xmemcli — xmemory command-line client
Single-command CLI for reading from, writing to, and managing xmemory instances over the HTTP API at $XMEM_API_URL (default https://api.xmemory.ai), using an API key from the Console UI or xmemcli auth login.
Full command reference is included below.
Usage
xmemcli auth login [URL] [--auto-approve] [--no-browser] [--timeout S] [--console-url URL] [--callback-port N] [--email ADDR [--org-name NAME]]
xmemcli auth logout
xmemcli auth status
xmemcli read <query>
xmemcli write <text>
xmemcli write (--mutations-file PATH | --mutations-stdin) [--delete TYPE:ID]…
xmemcli write --delete TYPE:ID [--delete TYPE:ID]…
xmemcli write-status <write_id> [<id> …]
xmemcli quota
xmemcli instance templates
xmemcli instance create --name NAME (--template ID | --schema-file PATH | --schema-stdin)
xmemcli binding list [--autoload]
xmemcli binding add <instance_id> [--tier autoload|available|off] [--scope project|user]
xmemcli binding remove <instance_id> [--scope project|user]
xmemcli context [--text] [--max-tokens N] [--no-live-state]
xmemcli trace ls [--instance ID]… [--trace-type T]… [--hours-back N] [--user-id U] [--api-key-id K] [--limit N] [--cursor TS_MS:TRACE_ID] [--counts-only]
xmemcli trace ls --search [--text …] [--request …] [--response …] [--object NAME]… [--field NAME]… [--status S]… [--trace-id ID]… [--session-id S] [--instance ID] [--trace-type T|delete]… [--hours-back N] [--include-llm] [--limit N] [--cursor TS_MS:TRACE_ID:INSTANCE_ID]
xmemcli trace get <trace_id> [--trace-type write|read|create|update|evolution]
xmemcli trace calls --session-id S [--stage S] [--model M] [--outcome succeeded|failed|refused] [--hours-back N] [--limit N] [--cursor TS_MS:TRACE_ID:INSTANCE_ID]
xmemcli trace call <llm_call_id>
Global flags / env: --api-key / $XMEM_API_KEY, --instance-id / $XMEM_INSTANCE_ID, --api-url / $XMEM_API_URL, --rc-dir / $XMEM_RC_DIR, --binding-dir / $XMEM_BINDING_DIR, --json, --verbose. See xmemcli help options. trace … and auth login additionally take --console-url / $XMEM_CONSOLE_URL (the Console origin; inferred for the public, stg, pp and local pairs and the /console sibling of a /xmem base).
Credential resolution: --api-key → $XMEM_API_KEY → nearest .xmemrc.json (walk up from --rc-dir toward $HOME). Origin: --api-url → $XMEM_API_URL → rc api_url → default. The mcp transport resolves its own origin the same way: --mcp-url → $XMEM_MCP_URL → rc mcp_url → the API base's /mcp sibling or hosted pair (stg, pp, dk) → default, where mcp_url is what the API told auth login about itself.
context is the exception: it runs unattended from a session-start hook, with no person and no chosen directory behind it, so it resolves the credential from $HOME only — a project .xmemrc.json is used only when --api-key / $XMEM_API_KEY or --rc-dir / $XMEM_RC_DIR names it explicitly. That stops a cloned repository shipping the key and origin its own context is fetched with.
Two local files, same discovery rule, different jobs: .xmemrc.json holds the credential (0600, never committed, nearest wins); .xmemory.json holds the instance binding (0644, meant to be committed at project scope, every scope merged). binding commands are local-only — no network, no credential.
Read / write modes
| CLI | API field |
|---|---|
xmemcli write --extraction fast (default) |
extraction_logic: "fast" |
xmemcli write --extraction deep |
extraction_logic: "deep" |
xmemcli write --no-wait |
async write; poll with write-status |
xmemcli write --mutations-file m.json / --mutations-stdin |
structured_mutations — the JSON array as given; no text, no extraction_logic |
xmemcli write --scope Pet:name=Luna --scope-mode drop |
scope: {objects: [...], mode: "drop"} — out-of-scope changes are skipped and reported; reject is not sent |
xmemcli write --delete Person:name=Ada |
appends {"object_mutation": {"object_type": "Person", "delete": {"key": {"name": "Ada"}}}} (Person:<xuid> sends {"xuid": …} as the key) |
xmemcli read --read-mode single (default) |
mode: "single-answer" |
xmemcli read --read-mode raw |
mode: "raw-tables" |
xmemcli read --read-mode xresponse |
mode: "xresponse" |
xmemcli read --related-types |
include_related_types: "types" — the response's related_types object is kept in the curated output |
xmemcli read --related-types-depth 2 |
include_related_types: "types" and related_types_depth: 2 — the catalog entries carry their distance and, below the last level, their own edges |
--read-mode selects the server-side answer shape; --json and the TTY rule govern stdout format.
Terminal colors
Interactive help and trace JSON use a dark-terminal palette by default. When COLORFGBG reports a white background (7 or 15), xmemcli uses darker colors for light terminals. Set XMEMCLI_THEME=light or XMEMCLI_THEME=dark to choose explicitly when the terminal does not report its background. NO_COLOR still disables colors.
Curated output
The CLI does not echo raw API payloads. Server internals (sql, diff_plan, extraction trees) are never emitted. Read responses keep pending_suggestions (schema-evolution hint). A text write keeps a compact extracted summary (Type(identifier) tags); a structured write runs no extraction and has none. write and write-status keep the server's changes block (created / updated with old → new / deleted, bulk summaries, advisory records) when the write changed something. --verbose adds trace_id and console_url when present.
trace … is the one deliberate exception. Those commands return the Console's own operation documents — the paged operations list, the Inspect search, and the per-operation detail — verbatim, because the Console already curates them per caller (a super admin sees LLM calls and raw token counts; everyone else does not). They are JSON on every stream and carry every internal id the Console does: trace_id, instance_id, session_id, user_id, api_key_id, and on detail documents source_id, migration_id, llm_call_id, gateway_request_id, …
Trace — the Console's operation traces, from the CLI
xmemcli auth status # super_admin: which Console view trace will answer with
xmemcli org list instances # the instances this key can see — what trace ls is scoped to
xmemcli trace ls # every visible instance, newest first, one page
xmemcli trace ls --instance "$ID" --trace-type write --trace-type read --limit 50
xmemcli trace ls --counts-only --hours-back 168 # counts, per-instance counts and series, no rows
xmemcli trace ls --search --text "Ada" --instance "$ID" # Inspect search — opt-in, more expensive
xmemcli trace get 0001_abc --trace-type write # one operation, every internal id
xmemcli trace calls --session-id "$SESSION" --stage 'benchmark.*' # a session's LLM calls (super admins)
xmemcli trace call "$LLM_CALL_ID" # one LLM call whole: prompt, reply, stats
Paging is a cursor the previous page returns. Pipe a page to jq with printf '%s\n', never echo: under zsh or dash echo rewrites backslash escapes inside the JSON. Stop on a non-zero exit: an error is never the last page.
PAGE=$(xmemcli trace ls --instance "$ID" --limit 100) || exit
# `select(.has_more_operations)` so the last page yields an empty string rather than the literal `null:null`,
# which `--cursor` refuses.
NEXT=$(printf '%s\n' "$PAGE" | jq -r 'select(.has_more_operations) | "\(.next_before_ts_ms):\(.next_before_trace_id)"')
[ -n "$NEXT" ] && xmemcli trace ls --instance "$ID" --limit 100 --cursor "$NEXT"
--search pages too, with the Inspect endpoint's three cursor fields. Follow has_more until it is false: a page can come back short, even empty, and still have more. Each page is a full search on the Console, so walk with --limit 500, the Console's cap:
CURSOR=
while :; do
# Any non-zero exit ends the walk without its last page: exit 3 with stage `paging_unsupported`, say, is a
# Console that ignored the cursor.
if [ -z "$CURSOR" ]; then
PAGE=$(xmemcli trace ls --search --text "Ada" --limit 500) || exit
else
PAGE=$(xmemcli trace ls --search --text "Ada" --limit 500 --cursor "$CURSOR") || exit
fi
printf '%s\n' "$PAGE" | jq -c '.merged[]'
case "$(printf '%s\n' "$PAGE" | jq -r '.has_more')" in
true) ;;
false) break ;;
*) echo "no has_more in the answer: this Console does not page" >&2; break ;;
esac
CURSOR=$(printf '%s\n' "$PAGE" | jq -r '"\(.next_before_sort_at_ms):\(.next_before_trace_id):\(.next_before_instance_id)"')
done
trace calls pages the same way, with the same three cursor fields:
PAGE=$(xmemcli trace calls --session-id "$SESSION") || exit
NEXT=$(printf '%s\n' "$PAGE" | jq -r 'select(.has_more) | "\(.next_before_sort_at_ms):\(.next_before_trace_id):\(.next_before_instance_id)"')
[ -n "$NEXT" ] && xmemcli trace calls --session-id "$SESSION" --cursor "$NEXT"
--include-llm adds model-call hits to a free-text search (--text, optionally with --session-id or --hours-back), for a super admin's key only; any other key gets the operations it gets without the flag and no calls. The CLI refuses the flag with a clause flag or an instance, user or key scope, where the Console's search finds no model call. When a page ends on one, its llm_call_id is the cursor's third field, so repeat the flag on every page of that walk.
A search with no filter shaping it is the Console's recent-activity view, which reaches back only as far as its window (currently 180 days); when older operations exist, its last page says truncated and the CLI warns. A key sees the operations of the instances it can list — never more than its owner sees in the Console; a super admin's key sees what a super admin sees. Full reference: .
Output personality — JSON vs pretty
- Non-TTY stdout or
--json: exactly one JSON document. - Interactive TTY without
--json: short one-line summaries per command.
Scripts can rely on xmemcli … | jq without --json.
Example session
export XMEM_API_KEY="xmem_..."
export XMEM_INSTANCE_ID="<uuid>"
xmemcli write "John likes orange"
xmemcli read "what colour does John like?"
ID1=$(xmemcli write --no-wait "Ivy likes amber" | jq -r .write_id)
ID2=$(xmemcli write --no-wait "Lev likes indigo" | jq -r .write_id)
xmemcli write-status "$ID1" "$ID2"
Install
Requires Python 3.12+. Stdlib only — no runtime dependencies.
Preferred:
uv tool install xmemcli
When uv is not available:
pip install xmemcli
Then:
xmemcli version
xmemcli auth login
Version: 1.8.0.
xmemcli auth flow — PKCE handoff, email sign-in, and credentials
The CLI is human-approved for key acquisition: an AI-assisted IDE may run reads, writes, and inventory, and may even initiate key acquisition, but a key is only ever issued after one explicit human approval — a click in the browser (PKCE handoff) or an approval of a sign-in email (--email). The one exception derives from such a key rather than replacing the approval: org create key lets a key that was already approved mint a key no wider than itself, for the same user, on one of its own clusters, deactivated with it (see below). A key must never enter the AI transcript — it is handed to the CLI out-of-band via xmemcli auth login or environment / .xmemrc.json, or written to the 0600 --out file of org create key, and the CLI prints only its prefix.
Two acquisition paths share xmemcli auth login:
- Browser PKCE handoff (default): the CLI sends the human to
/xmemcli/<challenge>on the Console, listens on an ephemeral127.0.0.1port named in that URL, and the Console delivers a signed short-lived code (not the key) to that callback — in the background where the browser allows it, otherwise through a link the human clicks. - Headless email sign-in (
--email <addr>): the CLI plays the waiting-browser role of the Console's cross-device email sign-in and then mints its own key — no browser on this machine. See Email sign-in below. - Zero-click browser handoff (
--auto-approve): the same PKCE handoff and the same page, opened with?auto_approve=1; the Console then shows no controls, obtains a code carrying an intent to mint a key namedCLI auto-approved login (<host>, <timestamp>), and navigates the tab to the loopback callback by itself; the key is created when the CLI redeems that code with its verifier. See Zero-click handoff below.
Scope. Shipped in this package:
.xmemrc.jsondiscovery, PKCEauth login/logout/status, emailauth login --email,/whoamiconsumption, andquota. Server endpoints:POST /cli/handoff,POST /cli/token, and — for the email path — the Console sign-in and accounts routes listed below (all pre-existing Console surfaces; the email path added no server endpoint).
Acquiring a key
The human either:
- Provides a key they already hold (
$XMEM_API_KEY,.xmemrc.json, or paste at login), or - Creates a key in the Console and clicks "Use this key in the CLI" (when the page was opened via
/xmemcli/<challenge>), or - Approves a sign-in email for an
auth login --emailrun, after which the CLI mints its own key.
During onboarding, the Console may auto-handoff an onboarding key while a short-lived cookie bridge is active.
Why a code, not the key
Plaintext keys in URLs leak to history and proxies. Handoff uses PKCE + signed code + localhost callback:
- CLI mints
verifier, deriveschallenge=base64url(SHA256(verifier)), opens/xmemcli/<challenge>. - Human clicks "Use this key in the CLI" → Console
POSTs the key to/cli/handoffbound to the challenge → receives a short-livedcode. - Browser delivers to
http://127.0.0.1:<port>/callback?code=…&state=<challenge>— key never in the URL. - CLI
POST /cli/tokenwith{ code, verifier }→ receives key → writes0600.xmemrc.json.
Sequence
AI-assisted IDE ── xmemcli auth login ──► CLI: PKCE verifier + localhost listener
Human ── opens Console URL ──► creates key → "Use this key in the CLI"
CLI ◄── local callback ── redeems code + verifier → writes .xmemrc.json
AI-assisted IDE ── xmemcli read/write ──► CLI resolves key; never handles plaintext key
Zero-click handoff — --auto-approve
xmemcli auth login [<url>] --auto-approve is for a scripted onboarding that must not stop for a click. The logic is the browser handoff's, step for step — verifier and challenge, an ephemeral loopback listener named in the URL, POST /cli/handoff for a signed code, the code on the callback, POST /cli/token with the verifier, the 0600 rc — with one inversion: the key is created at the redeem, not before it. The Console creates nothing; it asks the server for a code that lets the holder of the verifier mint a key, and only the CLI that started the login holds the verifier.
- The CLI opens
/xmemcli/<challenge>?callback_url=http://127.0.0.1:<port>/callback&auto_approve=1&host=<hostname>. The parameter is what selects the zero-click surface; without it the same URL is the manual page. The callback is always named here, even for the legacy port the manual page would infer: this surface refuses a link without one. - If the browser holds no Console session, the Console's auth wall sends the human to sign in — email code, Google, GitHub or the deployment's OIDC provider, whichever they use — and returns them to the same URL with its query intact (
?next=). That return is for an existing account: an address signing in for the first time is sent to the Welcome page to create its account, which dropsnext, so the CLI waits out its timeout and the login must be re-run once onboarded. Nothing about the identity provider reaches the CLI; a session cookie is all the surface needs, and it waits for nothing else. - With a session, the surface
POSTs/cli/handoffan issue intent: the challenge and the key nameCLI auto-approved login (<hostname>, YYYY-MM-DDTHH:MM:SSZ)— the email path'sCLI email login (<hostname>, <timestamp>)shape with the method named — and no key. The hostname travels as&host=on the login URL, cleaned by the same rule on both ends (letters, digits,-._, at most 32, elseunknown-host). - The server, cookie-authed, decides whom the code may mint for: the session's account and organisation, the permission to create a key for oneself (
api_key.create_ownorcreate_all), and the role — the one namedDefault, else the organisation's only role, else a 409 rather than a guess. It signs those ids, the name, the session's email and its authentication time into the 120-second code (stash_intent): the same JWT as the manual handoff's, with noenc_keybecause there is no key. Nothing is created. - The surface navigates the tab (
location.replace) tohttp://127.0.0.1:<port>/callback?code=…&state=<challenge>. That is the very request the manual page's "Finish the login in a new tab" link makes on Safari — a top-level navigation, which WebKit's mixed-content rule does not cover and Chrome's Local Network Access permission does not gate — issued by script in the same tab instead of by a click on an anchor. Same-tab navigation needs no user activation (only new windows do), so it is the one delivery that is click-free on every engine, and no fallback link is needed.replace, notassign, so Back cannot land on a page that starts another handoff. - The CLI's listener takes the code, checks
state, andPOSTs/cli/tokenwith the verifier. This is where the key is born (_mint_from_intent): the server checks the challenge against the verifier and creates the key through the same service the API Keys page uses (create_api_key), attached to every cluster, as that user, with the session's authentication time so a revocation since the handoff is caught inside the create. What the handoff decided under the session is decided again inside that service's transaction, with the owner's row locked, not by the endpoint before it: the account still exists, is active, still carries the signed email (a rename since the handoff moves the revocation cutoff to the old address, which a cutoff check keyed by the current one would never consult), and still holdsapi_key.create_ownorcreate_allthrough its role — read with the role row locked, the lock a permission removal takes (remove_role_permission,update_role), so the removal is either visible to the mint or waits for the key to exist. A check made before that lock could be overtaken by either change committing between it and the insert. A super admin, read under the same lock, needs no permission row and binds any role, as the API Keys endpoint grants one. An intent mints exactly once: each carries an id, the key it mints records that id inapi_keys.handoff_intent_idunder a unique partial index, and a second redeem — concurrent, or after the first key was deactivated or renamed — fails on that index inside its own insert. Rows inapi_keysare never hard-deleted, so a consumed id stays consumed. Only that index's violation is a redeem; any other integrity failure of the insert (a role deleted underneath it) is an error, not a claim that a key exists. That second redeem is answered 409, naming the key and its prefix (names carry no uniqueness; same-second logins from one host are named alike): the caller proved the verifier, and what it needs is the key's name to find it under API → API Keys and deactivate it if it is still active, since a stored key's plaintext cannot be served again. The CLI prints that message verbatim and stops, instead of calling the code expired. A redeem whose reply is lost after the request was sent (a read timeout or a reset, which urllib raises bare rather than asURLError) is sent once more with the same code to the same URL, which yields the key if the first never arrived or that 409 if it did; lost twice, the CLI stops and says a key may exist to deactivate, rather than letting the callback worker die and the login wait out its timeout. The login's deadline bounds the wait for the callback, not the redeem: a callback captured in time — the listener's handler publishes the capture the moment it stores it, so the last instant before the deadline counts — is redeemed within the redeem's own bound (two sends at the redeem timeout, plus a second) even past the deadline, since the redeem is what makes the key exist, and a redeem that outlives that bound ends the login with the same ambiguity stated, as exit 2 rather than the timeout's 5. A callback that arrives after Ctrl+C, or after a pasted key won, is not redeemed at all; a pasted key is not used while a redeem is in flight, since that redeem's key is the one that will exist; Ctrl+C during a redeem says a key may exist, with its prefix when the reply landed in time. None of this touches the login without the flag. A super admin, whose session names no organisation, is issued the key in their own. The CLI writes the rc exactly as the manual path does. Its JSON output carries"auto_approve": truebeside"method": "pkce".
The surface shows only where it is or why it stopped; every failure it can show ends with "No key was issued.", which is true by construction. The one retry a person has is to re-run the login command they started, with its own flags (a positional URL, --api-url and --console-url, a pinned --callback-port) and --auto-approve; the copyable line on that surface is the command's simplest form, not a substitute for those flags. The flag cannot combine with --email (exit 2): that path has no page to approve on. The CLI's done page, which the tab lands on, says "Code received" and names the terminal for the result, because it is served before the redeem; it carries Referrer-Policy: no-referrer as a header and a meta tag, since its URL holds the signed code and the brand stylesheet and fonts it loads come from other hosts.
Why this needs no probe, and what remains. The manual page probes the listener (/permission-probe with the X-Xmemcli marker) before it mints in the background, because there a key already exists when the code is handed out. This surface cannot probe — a probe from a page load has no user activation, and Chrome denies it without asking — and does not need to: an authored ?auto_approve=1 link opened by a signed-in person delivers a code to a port on their own loopback, and unless something there redeems it with the matching verifier, nothing is persisted. A closed port, a browser error page, a link opened twice: none of them leaves a key behind. What the code exposes if captured is ids, a key name, an email and a timestamp, for 120 seconds, redeemable only with the verifier that matches its challenge.
The residual is the authored link itself: there the verifier belongs to whoever wrote the link, so anything able to read that loopback port on the victim's machine — another account's process on a shared box, a port forwarded in with ssh -L — could relay the code to the author, who redeems it for a key on the victim's account. This is accepted: a process on the victim's loopback already implies code execution as them, the same line the manual page's probe draws (cli_handoff.js), and the key such a relay yields is named for its origin and revocable on the API Keys page. The honest guard against it would be one click, which is what the flag exists to remove.
Email sign-in — --email
xmemcli auth login --email <addr> [--org-name <name>] acquires the key with one human action and no browser on this machine — the flow an agent-driven IDE uses. The CLI takes the waiting-device role of the Console's cross-device email sign-in; every endpoint below already served the Console before this flag existed. The fully headless path requires the server to have cross-device hand-off enabled; a server without it only offers the typed six-digit code, so a run with no interactive terminal is refused there (after cancelling the attempt it had to start to find out).
POST /api/kingdom-signin-request— the server emails a six-digit code + one-click link; the CLI holds the signed pending cookie in memory. The reply's matching code is consumed only as the hand-off signal and is not printed (the compare UI is retired across all sign-in surfaces for now).- The human opens the email on any device and Approves. This is the single human action.
- The CLI claim-polls
POST /api/kingdom-signin-claimon the Console's own waiting-tab cadence (a short grace, ten fast polls, then a slow poll; transient network failures count as missed polls, not aborts) and exchanges the proof viaPOST /api/kingdom-signin-mintfor the browser-session cookie — held in memory only, never written to disk. - With the session, the CLI runs the Console onboarding's core sequence:
GET /api/check-user; when the address has no account,GET /api/suggest-slug(server-derived org name,--org-nameoverrides; ignored for an existing account) andPOST /api/public-signup— note that creating a new organisation requires the deployment to allow public registration, which the hosted service currently does not: an existing account gets a key, a new address gets the server's "organisation creation is not available" refusal (the Console's admin-fallback signup arm is not implemented here); thenGET /api/accounts/users/by-email,GET /api/accounts/api-roles(the seeded default role, or the org's only role — an ambiguous set is refused, never guessed), andPOST /api/accounts/api-keyswith no cluster list — the key attaches to every cluster the org has at mint time. Clusters created later are attached by a server-side backfill that repairs only keys already linked to every other cluster in the org; an org with no clusters at mint time gets a key attached to nothing. The key is namedCLI email login (<hostname>, <timestamp>)so every mint stays individually identifiable and revocable on the Console's API Keys page. - The key is written to
.xmemrc.json(0600), stdout carries the prefix only, and the session cookie dies with the process.
That login key is attached to every cluster the org has at mint time. org create key --name … --role … --cluster … --out FILE later mints a second key, with the key already in use, bound to exactly one of those clusters and to a role no wider than the one in use. The owner must still hold api_key.create_own or create_all. The server accepts this only from the release that lets a key mint keys, which followed the release that taught every node to contain a key-minted key; an older server answers 403, or 422 for a --role name on a server older than #2873, and the CLI says which. A temporary mint limit answers 429, and its message says which: another mint by the same user still running, the user's keys past their per-minute budget, or a server tracking as many minting users as it can. A busy server answers 503. Neither creates a key, so both are safe to retry after a short wait (the server sends Retry-After, which the CLI does not show); from 1.7.8 the CLI says so. It tells an older server's 403 apart from the server's refusal of the key itself by the generic Insufficient permissions text alone, so the server may reword its own. The plaintext goes only to FILE, created 0600 before the mint and never over an existing file; stdout carries the prefix and the path, and nothing is written to .xmemrc.json. The new key records the key that minted it: it expires no later than that key, keeps its one cluster, and is deactivated when that key is. Login itself is unchanged.
The wait is bounded by --timeout — 600 seconds for this path by default, which is also a ceiling: nothing stays claimable past the server's pending window, so larger values are clamped. The emailed one-click link and six-digit code themselves expire at about five minutes; the wait continues past that because an approval given in time stays claimable, and the terminal says when the emailed artifacts have lapsed. The Console origin must be https (or a loopback host, for local development). The Console must also match the API origin the key will be used against: with a non-default --api-url the CLI only infers a Console where the layout determines one — a single-origin /xmem base names its /console sibling on the same host, and that sibling beats $XMEM_CONSOLE_URL on the same call — a hosted deployment this client knows (api.stg / api.pp.xmemory.ai) names its console. host, and the local-dev convention pairs :8000 with :8002 — otherwise it refuses to guess (pass --console-url; $XMEM_CONSOLE_URL only when --api-url was not given). Because that inference exists, a single-origin deployment's rendered sign-in command names the API alone; every other layout still renders the --api-url/--console-url pair, since naming one without the other is worse than naming neither (api/agent_setup_renderer.py), and an explicitly named Console that provably mismatches the API origin (mixed loopback-ness, a default-production half paired with a non-default one, or a stg / pp half paired with anything but its own origin; a single-origin /console beside its own /xmem on one origin is one deployment, even on a stg or pp host, while the production halves are still held to their defaults) is refused rather than trusted.
When the server offers no matching code on the request reply (cross-device hand-off disabled, no public Console origin configured, or a transient degradation), there is nothing for a headless starter to claim — the emailed link then signs in the approving browser — so the CLI falls back to the emailed six-digit code typed into the terminal (POST /api/kingdom-signin-verify), still a single human action. That fallback needs an interactive stdin; a non-interactive run cancels the attempt it just started (the mode is only known from the server's reply, after the email is on its way) and refuses with instructions — the typed code dies with that cancel, but on such a server the one-click link has nothing durable to revoke and stays redeemable in a browser until it expires (about five minutes), which the terminal states plainly.
A credential that already resolves (via /whoami) to the requested address at the requested origin — checked across --api-key, $XMEM_API_KEY, and the rc, in that order — short-circuits without sending any email, so re-running the command is free (a matching $XMEM_API_KEY is copied into .xmemrc.json so the project gains a durable credential; an explicit --api-key is never persisted); when the check itself cannot be made (the API is unreachable) the CLI refuses to mint rather than stranding a duplicate key. Every abort of a started attempt — Ctrl+C, timeout, or an error mid-wait — best-effort-cancels it (POST /api/kingdom-signin-cancel, retried briefly) and reports what the cancel actually achieved: a confirmed cancel of a cross-device attempt makes the emailed link unapprovable; an unconfirmed one is reported as such; and on a hand-off-disabled server the link has nothing durable to revoke — it stays redeemable (in the browser that opens it) until it expires on its own, and the terminal says so.
Credential store (.xmemrc.json)
Project-local .xmemrc.json: {email, api_url, api_key}. Found by walking up from --rc-dir / CWD, ceiling $HOME.
Those three keys are required and must be strings. Anything else in the file is ignored, not rejected (since 0.0.12): the rc is the only durable credential store, so a file this CLI cannot load is a CLI that cannot run any command at all — which would make adding a field to the file a breaking change far wider than the feature that added it.
Since 1.1.0 the file may also carry mcp_url — the MCP resource the API reported for itself when the key was issued, written only when the server names one. It is what lets xmemcli mcp reach an on-premise MCP host: that host is in no table the client was built with, and the rc is the one anchor a cloned .mcp.json does not control. A blank or non-string value is read as absent. It outranks the single-origin sibling inference below — a deployment naming itself beats a shape we derived — and both beat the built-in default. The mount path is part of the destination: https://host/mcp authorises that mount, not the sibling services beside it — and the instance id is canonicalised as a UUID before it is appended, so nothing following the mount can walk back out of it. Every lookup that reads mcp_url refuses redirects rather than merely dropping the credential across them, because what it learns is a host the key is later sent to. Every mutation of the file — write, in-place update, and logout's delete — is serialised under an exclusive lock on its containing directory, and an update is additionally bound to the identity and origin it was decided from. What protects an in-place update is that comparison, which is portable; the lock narrows what remains — the moment between comparing and replacing — where the platform offers one. A failed record is a warning, a failed de-authorisation fails the command. The enrichment write after login is conditional on the same comparison, so logging out or signing in again while it is in flight is not undone by it.
Resolution order: --api-key → $XMEM_API_KEY → .xmemrc.json. Origin: --api-url → $XMEM_API_URL → rc api_url → default — except when the key is explicit (--api-key / $XMEM_API_KEY): the rc's api_url is skipped and the origin falls back to the built-in default unless you also set --api-url / $XMEM_API_URL. The localhost-key-at-prod guard applies when the key comes from the rc and an explicit --api-url / $XMEM_API_URL mismatches that rc origin. A base URL's path is preserved, never stripped — on a single-origin deployment the API lives at https://host/xmem, and that mount is part of every request the CLI builds; query, fragment, and userinfo on a base URL refuse normalisation rather than being stripped, so sibling inference cannot run on a shape the caller did not supply. Console resolution for login: --console-url → Console pinned by a positional (or mistaken --api-url) single-origin URL → $XMEM_CONSOLE_URL when --api-url was not given → sibling or known-deployment inference from the call's API base (--api-url → $XMEM_API_URL → rc api_url) when it applies → the production Console only for the exact production API base; anything else is refused. The rc is read for the API origin only when no API is named on the call, and a file that cannot be read or decoded names no origin. An explicit --api-url suppresses $XMEM_CONSOLE_URL for that invocation (a five-host --api-url without --console-url is a usage error, not a fall-through to the env Console). A named API origin from $XMEM_API_URL or the rc is held to the same infer-or-refuse rule (a refusal for an rc origin names the file and how to sign in to production instead), so an env-only non-default API without a Console cannot mint at the hosted Console and record that key against the foreign API; an inferred sibling that is remote HTTP is refused under the same HTTPS-or-loopback rule as a positional login URL. An explicitly named Console (flag, env, or pinned) is also cross-checked against the API origin on this path — the browser redeem goes to that same Console, so a wrong one would mint the key, and the interactive paste fallback presents the pasted key to it as a bearer — and a provably mismatched pair (mixed loopback-ness, a production half paired with a non-production one, or a stg / pp half paired with anything but its own origin; a single-origin /console beside its own /xmem on one origin is one deployment, even on a stg or pp host, while the production halves are still held to their defaults) is refused before either worker starts, in the same words as the email sign-in. When the API comes from the rc: an origin that is neither https nor loopback (localhost, 127.0.0.1, [::1]) is refused (naming a bare origin with --api-url beside an https --console-url accepts it), and if that API names its own Console (a /xmem base its /console, a local :8000 its :8002, stg / pp their table Console), a named Console must be that one, in any spelling of that origin (case, a default port, trailing dots on a named host, localhost / 127.0.0.1 / [::1] for a loopback one) but on the same mount — any other is refused (exit 2), so a $XMEM_CONSOLE_URL exported for one deployment cannot mint a key into the rc of a deployment whose Console is known. Naming the API on the call makes the pair the caller's: --api-url with the Console in --console-url, or $XMEM_API_URL with it in --console-url or $XMEM_CONSOLE_URL. auth status, trace and the org permission probe hold a named Console to the same rule while the call names no API: the first two exit 2, saying how to keep that Console, and the probe declines to send the key and reports the original 403. There, naming the API on the call (--api-url or $XMEM_API_URL, which must match the rc's origin the key is bound to) lifts the rule, and the Console still comes from --console-url (trace) or $XMEM_CONSOLE_URL — unlike login, --api-url does not turn $XMEM_CONSOLE_URL off for these. The same resolved Console is passed to the post-login /whoami that records mcp_url, so a leftover $XMEM_CONSOLE_URL cannot steer that lookup either. When --api-url is present, $XMEM_API_URL is not consulted for Console inference. Because a mounted base cannot also serve the /api-prefixed spelling of a route, the compatibility candidate in whoami_urls / token_redeem_urls ({base}/api/whoami, {base}/api/cli/token — a root-served deployment's second form) is offered only for a path-less base. The MCP bridge resolves its endpoint as --mcp-url → $XMEM_MCP_URL → the rc's mcp_url → the /mcp sibling or hosted pair (stg, pp, dk; _login.HOSTED_DEPLOYMENTS) of the effective API base (--api-url → $XMEM_API_URL → rc → default) → default, and its foreign-origin guard accepts the /xmem ↔ /mcp sibling pair as one deployment.
Identity — /whoami
xmemcli auth status calls GET /whoami with the active bearer key and reports {authenticated, email, key_prefix}. Exit 0 when the key resolves; auth error when it does not.
The AuthApiKey body also carries mcp_url, this deployment's own MCP origin (null where it serves none). The field is always present, null included: an absent key means the server predates it, which is a different answer and is treated as one. auth login reads it from there — on both paths, since the email flow never calls POST /cli/token — and records it in the rc. The lookup is best-effort: any failure simply leaves the key out of the file, and the transport falls back to its table of shipped API↔MCP pairs.
Security model
| Threat | Mitigation |
|---|---|
| Key in AI transcript | localhost callback / in-process mint → 0600 store; login stdout shows key_prefix only; org create key writes its key only to a new 0600 --out file and prints the prefix and path |
| Key in URL | URL carries code only; key over TLS on handoff/token |
| Captured code replay | PKCE verifier never leaves CLI; code is TTL-bounded |
| CSRF on callback | state = PKCE challenge; redeem requires verifier |
| Wrong Console page | CLI button only on /xmemcli/<challenge> |
Authored /xmemcli/…?auto_approve=1 link opened while signed in |
the zero-click surface creates no key: it obtains a code carrying an intent and navigates to the person's own loopback; the key is minted only when /cli/token is redeemed with the matching verifier, and an intent mints exactly once (unique index on api_keys.handoff_intent_id). A closed port or a repeated link persists nothing. Accepted residual: the link's author holds that verifier, so a process able to read the victim's loopback port could relay the code to them — the same local-code-execution line the manual page's probe draws; the resulting key is named for its origin and revocable |
| Session token outliving the login | the email-path session cookie is held in process memory only — never printed, never on disk — and is discarded when the process exits; the token itself stays server-valid until its ~2-day expiry, so the containment is the CLI never letting it out of memory, not revocation |
| Session cookie over cleartext | the email path refuses non-https Console origins (loopback excepted), refuses every redirect on its cookie-carrying requests, and fails fast when a tunnelled Console marks its cookie Secure for an http:// origin |
| Unsolicited sign-in email initiation | server-side send limits per mailbox (enforced per server node, so the fleet-wide budget scales with node count); the email itself grants nothing without the inbox owner's Approve, and the CLI best-effort-cancels attempts it cannot complete |
| Approving someone else's email sign-in | user-mediated — the confirmation page leads with "only if this is your address" and states that approving lets the requesting device act on the account, including creating API keys; the stake is higher here than in the browser flow, because approving a CLI-started attempt ends in a durable API key, not a two-day browser session. The matching-code comparison that once narrowed this further is retired for now (the code still travels on the wire but no surface displays it). Approve only sign-ins you started. |
Each login binds its own port and names it in the login URL, so concurrent logins never contend for one listener. Security rests on PKCE and on the callback being reachable only from the CLI's own machine, not on port secrecy. For SSH or devcontainer use the port has to exist before the tunnel does, so pin it: --callback-port <n> or $XMEM_CALLBACK_PORT, then forward that port.
Quota (observe vs escalate)
xmemcli quota observes usage freely. Raising limits requires human approval in the Console — the CLI must not self-grant quota increases.
xmemcli — capabilities reference
Version: 1.8.0 (see xmemcli version)
xmemcli is the command-line client for the xmemory HTTP API. It is human-approved for key acquisition: an AI-assisted IDE may run reads, writes, and inventory, and may initiate auth login, but a key is only issued after one explicit human approval — a click in the Console UI (PKCE handoff), an approval of a sign-in email (--email), or, with --auto-approve, the Console session the human already holds in that browser (signed in before, or right then through the Console's own email, Google, GitHub or OIDC sign-in). The one exception derives from such a key rather than replacing the approval: org create key lets a key that was already approved mint a key no wider than itself, for the same user, on one of its own clusters, deactivated with it. Quota limits change only in the Console UI. The full acquisition contract is in the auth-flow reference bundled with this package.
xmemcli … # installed CLI
Commands
Every command below has dedicated help — see Help.
Data
| Command | Description |
|---|---|
write [text] |
Sync write (POST …/write). --extraction fast|deep (default fast). --no-wait queues async write, returns write_id. --scope TYPE:ID (repeatable) anchors the write to existing objects: only they may be modified/deleted; by default new objects and links to them are allowed and anything else fails, and under --scope-mode drop only the objects a --scope names may be created and everything else is skipped; works with either extraction mode. --scope-mode drop (needs --scope) skips out-of-scope changes instead of failing and lists them under changes.skipped_out_of_scope (a server change, not a CLI one: past 100 entries the server folds the rest into lines shown with folded=true and no key or fields); it creates only records a --scope names by primary key, and such a record need not be stored yet — create-or-update exactly the named record. reject is the server default and is not sent. Instead of text, a structured write sends structured_mutations — deterministic creates, updates and deletes with no extraction: --mutations-file PATH or --mutations-stdin (one JSON array, same shape as the API's structured_mutations; see Structured writes) and/or --delete TYPE:ID (repeatable, --scope syntax: Person:<xuid> or Person:name=Ada; appended after the file's entries). Text and mutations are exclusive, as are the file and stdin forms; mutations refuse --scope and --extraction deep; empty or whitespace-only text is refused (exit 2, before anything is read or sent). A text write's output lists what it extracted as Type(identifier) tags (extracted); a structured write's does not. Both carry the server's changes block (created / updated with per-field old_value → new_value / deleted, and any other bucket such as created_keyless_objects) whenever the write changed something, and on a drop-mode write that skipped everything, where the block carries skipped_out_of_scope alone; a scoped write that left a scoped record untouched carries it too, with untouched_scope_records. A --no-wait answer carries only the write_id; write-status reports the changes once the write completes. |
write-status <write_id> … |
Poll async writes until terminal or --timeout (default 60s). Accepts multiple ids. A completed write's non-empty changes block is kept, as on write. |
read <query> |
Read from active instance. --read-mode single|raw|xresponse, --scope TYPE:ID (repeatable), --scope-relations, --related-types (also return related_types: per object type the read touched, the fields it did not return and the object types a declared relation links it to; needs instance.get_own on the key), --related-types-depth N (1, 2 or 3, refused as a usage error otherwise; follow the relations N levels out, each catalog entry saying its distance; implies --related-types). |
Requires --instance-id or $XMEM_INSTANCE_ID for read/write (or auto-pick when exactly one instance is visible — see Global flags).
Structured writes
--mutations-file PATH / --mutations-stdin send one JSON array as the API's structured_mutations, as given. The server takes at most 100 entries per write, --delete entries included; the CLI refuses more with exit 2 before sending anything. --mutations-stdin needs a pipe or a file on stdin and refuses a terminal. Each entry is one of:
object_mutation—{"object_mutation": {"object_type": "Person", "create": {"key": {"name": "Ada"}, "values": {"age": 36}}}}.updatetakes the samekey+values(the key may be{"xuid": "…"}; a null value clears a field);deletetakes{"key": {…}}alone.relation_mutation—{"relation_mutation": {"relation_type": "works_at", "create": {"endpoints": [{"object_name": "person", "key": {"name": "Ada"}}, {"object_name": "company", "key": {"name": "ACME"}}]}}}.createlists every participant role, each keyed by primary key or{"xuid": "…"}, with nokeyand novalues.deletetakes eitherendpoints(a subset may be given) or a top-level"key": {"xuid": "…"}— never both — and"allow_bulk_delete": trueto remove every matched link (without it, a delete matching more than one link is refused). Relationupdateis always refused: re-link by deleting and creating.
--delete TYPE:ID appends the object delete above; each key field may appear once and none may be empty. A delete that matches no record is not an error: exit 0 and no deleted line. The server lists it under changes.unmatched_deletes, which a terminal prints as note: unmatched_deletes Task task_id='T-999'; a server that predates that bucket reports nothing, and the write then reads write <id> ok · no changes reported.
Every current server accepts structured writes; an older one that had them switched off (execution.structured_writes_enabled, since removed) answers 400 Structured writes are not enabled on this deployment.; a server that predates structured writes answers 422 with two errors, both reported: Field required (field: text); Extra inputs are not permitted (field: structured_mutations). Both exit 3 with stage: "request".
Org inventory
Permission-filtered view of what this API key can see.
| Command | Description |
|---|---|
org list clusters |
Clusters visible to this credential |
org list instances |
Instances visible to this credential, as a bare array of records. A key minted with data.read but not instance.get_own (the supported shape for trace …) gets the ids only — the same set trace ls is scoped to — as a degraded document rather than an array: {"items": [{"id": …}, …], "degraded": true, "missing_permission": "instance.get_own"}, with the warning on stderr and in the document's warnings. The shape changes so a script cannot read an ids-only listing as a complete one; an array is never wrapped just to carry a warning. |
org list keys |
API keys visible to this credential (metadata only; plaintext never returned) |
org key [name-or-prefix] |
One key's role, its effective permission codes (the role plus a super-admin widening), and the clusters it is bound to when this credential can name every one of them. If it cannot, that field is unavailable, not a shorter list and not an empty one. A missing field is unavailable, not an empty grant. With no argument, the key this command is using, which the server marks in the list (is_caller); a server that predates that mark is matched by the stored prefix, and two keys that share it ask for a name. A selector is a name or a prefix of the stored prefix; a longer value is not a key, and an error keeps only the first eight characters of an xmem_ selector. |
org create key --name --role --cluster --out |
Mint a key for this user bound to exactly one cluster this key can already see. --cluster is a name or an id; --role is the role's name (org key shows the role of each key you hold), or its id when two roles share the name. The new role cannot grant a permission this key lacks, and the owner must hold api_key.create_own or create_all. The key is written only to --out, a new file created 0600 (an existing file is refused); output carries key_prefix and key_file, never the key, and nothing goes to .xmemrc.json. The new key keeps that one cluster (clusters created later are not added), expires no later than this key, and is deactivated when this key is, or unlinked from the cluster when this key is. To contain a leaked key, deactivate it in the Console: what it minted goes with it. A lost reply or a 5xx says a key may still exist, except the server's own 503 (busy), which created nothing; a 429 is a temporary mint limit whose message says which (another mint by this user is still running, this user's keys created too many keys recently, or the server is tracking as many minting users as it can), and a 400 a request the server refuses (such as a --name over 255 characters): neither created a key, and a 429 or 503 is safe to retry after a short wait (the server's Retry-After is not shown). A 404 means --cluster is not linked to this key; a 422 that names api_role_name means the server predates this command, which needs a server from the same release as this CLI; a 403 saying only Insufficient permissions means the server predates the release that lets a key create keys, and any other 403 that it will not mint this key: the role, the owner's permission, this key or the cluster. |
Instances
| Command | Description |
|---|---|
instance get <instance_id> |
Fetch one instance |
instance templates |
List the ready-made templates a create can name — id, label, one-line description, who each is for, example writes and reads, and the object-type names. No schema crosses the wire; the server holds the shape. |
instance create |
Create from a template or an XMD/JSON schema. Required --name; then exactly one of --template <id>, --schema-file or --schema-stdin. --template sends only the id: no schema is composed, generated or repaired, so the shape you get is exactly the one you picked. |
instance instructions [instance_id] [text] [--clear] |
Read, set or clear the instance's standing instructions to an agent — the owner's own words, carried to every agent that connects it. No text and no --clear reads and changes nothing. Setting reads the current value first and writes with the epoch it read, so an edit composed against instructions someone has since replaced is refused rather than applied (the console form and the instance chat write the same field). Clearing is --clear; an empty string is refused, because that is what a shell substitutes for an unset variable. The id may be pinned with --instance-id or $XMEM_INSTANCE_ID and the text given alone — a lone positional that is not an id is read as the text. |
instance setup [instance_id] [--format agent|project] |
How to connect this instance to an agent, ordered for where it is likely to be used. Prints the same steps the get_setup_instructions MCP tool gives an agent, so a person and the agent beside them read the same thing. --format project additionally prints the shared setup files to commit; each teammate still approves the install and signs in once. Carries no credential. |
Schema & XMD
XMD (xmemory Data) is the typed schema format for instances. These commands mirror the Console schema workflow (read/update/dry-run/migrations, LLM generate/enhance, and validation).
Command map
| User task | CLI command | Notes |
|---|---|---|
| Read live schema | schema get [instance_id] |
Live schema for one instance. -o writes YAML. |
| Apply migration | schema update [instance_id] |
--schema-file, optional --migration-plan, --confirm-destructive. |
| Preview migration | schema dry-run [instance_id] |
Same flags as schema update; returns planned DDL without applying. |
| List migrations | schema migrations list [instance_id] |
Newest first. --limit, --before-id, --include-yaml. |
| Fetch one migration | schema migrations get [instance_id] <migration_id> |
Optional positional instance id; else --instance-id / $XMEM_INSTANCE_ID. --include-yaml. |
| Review suggestions | schema suggestions review [instance_id] |
Suggestion engine: consolidated proposal from read-traffic gaps. |
| Decide suggestions | schema suggestions decide [instance_id] |
--proposal-version (required) + --accept/--reject/--defer/--file. |
| Apply suggestions | schema suggestions apply [instance_id] |
--proposal-version plus mandatory --confirm-destructive; preview removals in Console first. |
| Enhance bound schema | xmd enhance --from-instance <description> |
Uses live schema; requires instance id. |
| Synthesize schema | xmd generate <description> |
Cluster-scoped LLM synthesis. -o writes YAML. |
| Enhance from file | xmd enhance [schema_file] <description> |
From a file, or --from-instance for bound enhance. -o, --plan-output. |
| Create instance | instance create |
--name, --schema-file or --schema-stdin. |
| Validate schema | xmd validate / validate-yaml / validate-json |
Cluster-scoped server validation. |
| Convert JSON Schema | xmd convert |
JSON Schema → XMD YAML via the API (validate_json_schema). |
Not exposed in CLI (Console-only today): the suggestions before/after YAML preview.
Typical workflow
# 0. Or skip 1-2 entirely: pick a ready-made shape
xmemcli instance templates
xmemcli instance create --name demo --template personal_crm
# 1. Synthesize or enhance
xmemcli xmd generate "people and their pets" -o schema.yml
xmemcli xmd enhance schema.yml "add a Pet.breed field" -o next.yml --plan-output plan.json
# 2. Validate before create or update
xmemcli xmd validate next.yml
# 3. Create instance OR migrate existing
xmemcli instance create --name demo --schema-file schema.yml
xmemcli schema dry-run INST_ID --schema-file next.yml --migration-plan plan.json
xmemcli schema update INST_ID --schema-file next.yml --migration-plan plan.json --confirm-destructive
# 4. Inspect history
xmemcli schema migrations list INST_ID
xmemcli schema migrations get INST_ID MIGRATION_UUID
# 5. Suggestion engine (from real read traffic) — confirm with the user before decide/apply
xmemcli schema suggestions review INST_ID
xmemcli schema suggestions decide INST_ID --proposal-version PV --accept FP1 --accept FP2
xmemcli schema suggestions apply INST_ID --proposal-version NEXT_PV --confirm-destructive
Commands
| Command | Description |
|---|---|
schema get [instance_id] |
Live XMD schema. Optional -o file. |
schema update [instance_id] |
Replace schema from --schema-file. Optional --schema-type, --migration-plan, --confirm-destructive. |
schema dry-run [instance_id] |
Preview migration (same schema/plan flags as update). |
schema migrations list [instance_id] |
Applied migrations, newest first. --limit (default 50), --before-id, --include-yaml. |
schema migrations get [instance_id] <migration_id> |
One record. Optional positional instance id; else global instance flags. --include-yaml. |
schema suggestions review [instance_id] |
Consolidated proposal from read-traffic gaps. Returns proposal_version + items. |
schema suggestions decide [instance_id] |
Record accept/reject/defer. Requires --proposal-version plus fingerprints or --file. |
schema suggestions apply [instance_id] |
Apply accepted items as one migration. Requires --proposal-version and --confirm-destructive. |
xmd generate <description> |
LLM-synthesize XMD. Optional -o. Requires cluster resolution. |
xmd enhance [schema_file] <description> |
LLM-augment schema from file, or --from-instance for live schema. -o, --plan-output. |
xmd validate <schema_file> |
Validate; YAML vs JSON inferred from .json extension. |
xmd validate-yaml <schema_file> |
Force YAML validation endpoint. |
xmd validate-json <schema_file> |
Force JSON Schema validation endpoint. |
xmd convert <json_schema_file> |
JSON Schema → XMD YAML via the API (validate_json_schema). Optional -o, --root-object. |
Instance id for schema * commands: positional [instance_id], else --instance-id / $XMEM_INSTANCE_ID.
Binding (local only — no network, no credential)
Which instances an agent working in this directory should know about, and how eagerly to
engage each one. Stored in .xmemory.json, discovered by walking up from --binding-dir /
$XMEM_BINDING_DIR (or the cwd), ceilinged at $HOME — the same rule .xmemrc.json has always
used, and no git anywhere. From a start outside $HOME the walk checks that directory and
stops, rather than climbing into a shared parent like /work or /tmp where another user's file
could be planted. A session-start hook passes the project root explicitly, so it never depends on
the walk at all.
~/.xmemory.json is consulted as the outermost scope whenever $HOME is the user's own rather than part of the tree being read. Where the session root is the home directory — a dotfiles repository, a devcontainer or an archive unpacked as $HOME — that file is treated as project scope like any other file inside the tree.
Unlike the rc — where the nearest file simply wins — every scope is merged, git-config style:
~/.xmemory.json supplies personal instances, a repository's committed .xmemory.json adds the
team's, and the nearer file wins field by field on any instance both mention.
| Command | Description |
|---|---|
binding list |
Merged view for this directory. --autoload lists only what a session-start hook would pull. |
binding add <id> |
Bind an instance, or update the binding it already has. --name, --purpose, --tier, --engage (repeatable), --scope. |
binding remove <id> |
Unbind from one scope. To silence an instance inherited from a wider scope, bind it here with --tier off instead. |
context |
Session-start pack for the autoload-tiered bindings here. --text prints the pack alone, --max-tokens, --no-live-state, --timeout. The only one of these that needs a credential. |
Tiers: autoload (pull its context every session) · available (default; engage on demand) ·
off (bound but dormant).
Scopes: --scope project (default) writes the committable file — at an existing nearer
binding, else the git work-tree root when git can say and the reader would actually look
there, else the cwd. git only ever suggests: no git, or a directory that is not a checkout, is
an ordinary state and never blocks a write. The one refusal left is when the target would resolve
onto the home directory, which would write the user-scope file while calling it a project one.
--scope user always writes ~/.xmemory.json.
context makes no request when nothing is tiered autoload, and resolves no credential
either — a hook running on every session start must not error in a project that was never
going to fetch anything. A server without the endpoint is treated as nothing to inject, so a
client ahead of its deployment degrades quietly instead of failing every session, as does a
binding this build cannot parse.
--timeout bounds the whole command. Not the request — everything: binding discovery,
the credential preflight, the git provenance lookup, name resolution, TLS, response headers and
body. It is a wall-clock limit, because it is the only bound a session-start hook has (POSIX
sh has no portable timeout) and a bound with an exception in it is not one. Expiry degrades
like every other failure: exit 0, empty pack, one warning: line naming the budget.
--text prints the pack and nothing else, for a caller that will wrap it. Do not point a
hook at it directly: a hook's stdout is parsed as its control document on some events, so a
pack that happened to be valid JSON would be read as control fields rather than injected. A
companion editor-integration plugin wraps this output in the documented hook envelope its own
client expects; it ships from a separate repository and is not part of this one.
No secrets. An instance id is not a credential, so a project .xmemory.json is written
0644 and is meant to be committed — the opposite of .xmemrc.json (0600, never
committed). ~/.xmemory.json is written 0600: it stays on one machine, and on a shared host
its instance names and purposes are nobody else's business.
Scope precedence has one exception: your own entries are a ceiling. A nearer scope normally
wins field by field, but a project file arrives by git clone and is the less trusted of the
two. So for any instance ~/.xmemory.json lists, a committed file may make it less eager,
never more:
- Tier. Ranked
autoload>available>off. A project may take yourautoloaddown toavailableoroff; it can never raiseofftoavailable, oravailabletoautoload. An omittedtierin your file meansavailableand binds as one — sobinding add --scope user <id>with no--tiercaps that instance atavailableeverywhere. If you want a project'sautoloadto stand, say--tier autoloadin your own file: your entry states the most eager you are willing to be, not merely that you know the id. engage. Replaced by a nearer scope for every other instance, but not for one of yours — otherwise a committed file could rewrite the cues attached to your own instance, which is a quieter version of raising its tier.
Everything else (name, purpose) still merges nearest-wins, and a project may always add
detail to an instance you listed.
File format (v1). id is required; everything else is optional. Unknown keys are rejected,
so a typo fails loudly rather than being ignored.
{
"version": 1,
"instances": [
{
"id": "9c421cd4-77ab-4a51-a7e3-b8fd5d09d394",
"name": "Team Knowledge",
"purpose": "shared dev conventions",
"tier": "autoload",
"engage": ["a convention is learned or corrected"]
}
]
}
Trace — the Console's operation traces
What the Console shows on an instance's Operations tab (a paged list), on Inspect (a
search across operations), and in each operation's detail pane, plus (for super admins) the LLM calls of a
session, which no Console view lists — fetched from the same Console endpoints, with this CLI's API key, and emitted as the Console serves them. Nothing is curated
or reshaped: the Console already curates per caller, and a field the Console adds shows up here
the same day. These documents are for scripts and agents; on a terminal they are only indented
and coloured (NO_COLOR / FORCE_COLOR honoured). Flags only — there is no query language to
learn; the CLI composes the Console's search clauses itself.
| Command | Console view | Description |
|---|---|---|
trace ls |
Operations tab / Home | Operations, newest first, across every instance this credential can see (nothing given — the Home view), or the --instance ID given (repeatable, or a comma list; default --instance-id / $XMEM_INSTANCE_ID). Returns operations[], counts, instance_counts, series, and the paging cursor next_before_ts_ms + next_before_trace_id (with has_more_operations). Flags: --trace-type T (repeatable / comma; write, read, create, update, evolution — delete is --search only), --hours-back N (24 when not given, the Console's default for this list; 0 = unbounded) or --start-ts / --end-ts (epoch seconds), --user-id, --api-key-id, --include-console-reads, --bucket-ms, --limit N (default 100, Console cap 500), --cursor TS_MS:TRACE_ID (the previous page's two halves, joined with a colon), --counts-only (ops_limit=0: what Home fetches — counters and series, no rows; refused together with --limit / --cursor, which would have nothing to page). |
trace ls --search |
Inspect | The Inspect search, for the filters only it can answer: --text (free text), --request / --response (text on either side of the operation), --object NAME / --field NAME (repeatable; all must match), --status S (repeatable / comma; any may match: ok, error, stale, timed_out, internal_error, quota_exceeded, in_progress, schema-gap), --trace-id ID (repeatable / comma), --session-id; plus --instance (at most one — the Inspect scope), --trace-type (also delete), --hours-back (a floor applied to the hits after the search — Inspect's own recency windows decide the candidate pool, so this narrows a result, unlike the query window it is on trace ls), --user-id, --api-key-id, --include-llm (1.7.0: also model-call hits, in a free-text search — see below), --limit N (default 100, Console cap 500; a page can hold a few more rows than that when hits tie on time, trace id and instance id with its last one, and fewer when the Console narrows it), --cursor TS_MS:TRACE_ID:INSTANCE_ID (the previous page's three cursor fields, joined with colons). Returns the Inspect document: merged[] hits with kind, href (/write/{trace}, /read/{trace}, /create/…, /update/…, /evolution/…, or # for an instance deletion, which has no detail page), trace_id, instance_id, session_id, user_id, api_key_id / api_key_name / api_key_prefix, status, quota_kind (a quota_exceeded write or read only: daily_quota_exceeded or monthly_quota_exceeded; absent from an older Console), time_taken_ms, match_items; with --include-llm, for a super admin, model-call hits too: kind: llm_call, trace_id (the operation that made the call), llm_call_id, llm_operation_type, href (that operation's pane, or #), and llm_sub_stage, llm_provider and session_id when the call recorded them (the first two from a Console of 2026-10-08 or later); no instance_id and no status. Open one with trace call <llm_call_id>. Then the paging fields has_more, next_before_sort_at_ms, next_before_trace_id, next_before_instance_id, truncated. |
trace calls |
— (no Console view) | The LLM calls of one session, newest first, a page at a time. Super admins only: any other credential gets 403 → exit 3, stage permission. --session-id (required), --stage S (exact, or a prefix with a trailing *, e.g. benchmark.*), --model M (the model slot, or the model that served the call), --outcome (succeeded, failed — an error that is not a refusal — or refused), --hours-back N (server default 720, i.e. 30 days; 0 = everything kept), --limit N (default 100, Console cap 500), --cursor TS_MS:TRACE_ID:INSTANCE_ID (the previous page's three cursor fields: the call time, its operation and its call id). Returns llm_calls[] — per call llm_call_id, operation_id, operation_type, instance_id, session_id, sub_stage, model_type, model_id, provider, provider_type, called_at / called_at_ms, time_taken_ms, token counts, is_success, is_refusal, is_cached, error_message, finish_reason, gateway_request_id, client_attempts, gateway_repairs, reissue_of_llm_call_id, reissue_reason, the requested settings, the applied ones (applied_temperature, applied_thinking, applied_effort), the prompt-cache counts (cache_read_tokens, cache_write_tokens) and the prompt renderer (prompt_family, prompt_generator, prompt_schema_provider, prompt_version); never the prompt or the reply (an error_message may quote the gateway's detail about a reply) — and the paging fields has_more, next_before_sort_at_ms, next_before_trace_id, next_before_instance_id, truncated. |
trace call <llm_call_id> |
— (no Console view) | One LLM call whole, as {"found": true, "llm_call": {…}} (so jq .llm_call.prompt): the same fields as a trace calls row plus prompt, json_schema, result, raw_result (the reply as the model wrote it, when the gateway repaired it) and rejected_attempts. It does not list the calls that re-issued this one (trace get on the operation shows those as reissued_as_llm_call_ids). If the call's stats never landed, llm_call carries only llm_call_id, operation_id and those logged fields. Super admins only, as above. An unknown id — the Console's {"found": false} — is stage: "not_found", exit 3; so is a listed call whose logged half (prompt and reply) never landed. |
trace get <trace_id> |
Detail pane | One operation's full document. --trace-type (operation_type on a trace ls row; the first path segment of a --search hit's href) makes it one request; without it the five detail endpoints are probed in order write, read, create, update, evolution and the first that knows the trace answers. A deletion's DL00000000_aaaaaa (or original DL0000_aaa) id is answered without a request: it has no detail page. A write's document carries extracted_objects (what extraction produced) and cleaned_objects (what the write kept after cleaning, rendered as a synchronous SDK /write answer renders it, by the caller's own primary keys; the answer may list fields and a relation's endpoints in another order), each a list holding one JSON document. A keyless object's #N in cleaned_objects is numbered within that field, as in the /write answer (over the cleaned objects, plus a structured write's relation endpoints), so it can name another object than the same #N in the document's diff_plan, identity_changes and written_objects: a keyed object joins across these fields by its primary key, and a keyless one cannot be matched across them by #N. cleaned_objects is [] for an edit, a failed write, a write still in progress, a write that cleaned nothing or whose objects could not be rendered, a write on an instance without a schema, and writes recorded before the Console stored it. Both go to everyone who may open the write. A miss — the Console's {"found": false}, or its 404 for a trace outside your scope — is stage: "not_found", exit 3. |
--search is opt-in, on purpose. The Inspect search runs text predicates across the trace store with a candidate pool of thousands and a merge — markedly more expensive than the indexed, cursor-paged trace ls. Passing a search-only flag (--text, --request, --response, --object, --field, --status, --trace-id, --session-id) without --search is a usage error (exit 2) whose message says exactly that, so an agent reasons about whether it needs the search or whether trace ls narrowed by --instance / --trace-type / --hours-back plus trace get will do. Conversely --counts-only, --start-ts / --end-ts, --bucket-ms are refused with --search because the Inspect endpoint cannot honour them, and --include-console-reads because Inspect's only spelling of that toggle is a bare phrase inside q itself — which is also why a free-text value containing the words "include console reads" is refused rather than sent (the Console would flip the toggle and strip the phrase from the query).
Breaking change in 1.4.0: trace ls --search now asks the Console for one page (100 rows by default) instead of the whole capped result, under the Console's paging version 2 (paging=2), in which every search mode pages. A single call is no longer the complete answer: loop on has_more, and do not read a row count, or an absent warnings array, as completeness. A Console that predates paging still answers whole and capped, and the CLI tells it apart by the absence of has_more, not by the rows: a Console that pages sends the paging fields even when it found nothing. What it then warns about depends on what that Console reports. One that reports truncated gets a warning only when it says truncated: true, naming the ceiling of its mode; truncated: false is a whole answer and gets none. One too old to report truncated gets a warning on every answer: the CLI's own estimate when the row count reaches a ceiling, otherwise that this Console does not page searches and its answer may be capped.
Paging a search — read this before scripting --search. trace ls --search pages like trace ls, with the Inspect endpoint's own keyset cursor: pass the previous page's next_before_sort_at_ms, next_before_trace_id and next_before_instance_id back as --cursor TS_MS:TRACE_ID:INSTANCE_ID until has_more is false. A model-call hit has no instance, so when a page ends on one, next_before_instance_id is its llm_call_id: pass it back as it came, and give --include-llm on every page of that walk, since the cursor is a place in the result that flag shapes. Follow has_more, never the row count: the Console narrows each page after its row limits (type and status resolution, console-read exclusion), so a page can hold fewer rows than --limit — even none — and still have more. Paging reaches every match with two exceptions. Free text (--text) shorter than three characters does not match the text inside finished operations — a write's text and diff plan, a read's query and result, an operation's error message: the Console's text indexes on them hold three-character runs (trigrams), and rather than scan every payload it lets a needle with none match nothing there. The Console counts only ASCII characters toward the three, so a short needle with accented letters can miss the same way. Such a needle still matches an id, an exact object, field or type name, and an evolution's stage or error. The other exception the Console reports itself: a search with no filter that shapes the query (only scope such as --instance, --session-id, --user-id, --api-key-id or --hours-back) is the Console's recent-activity view, which reaches back only as far as its window (currently 180 days). When this credential has older operations than that, the last page carries truncated: true and the CLI emits a warning (stderr, and folded into the JSON document's warnings array) naming the way past it — a filter such as --trace-type or --text. That flag comes from the endpoint, which knows what it could not reach; against a Console that pages, the CLI does not guess at a cut from how many rows came back. Only a Console too old to report truncated still gets the CLI's own estimate from the row count, and that warning says it is an estimate. Asking for a page changes two things worth knowing before you script it: a free-text search answers from one candidate window per page rather than the exhaustive second pass the whole-result path ran, so a rare needle can give a short — even empty — first page with has_more: true where one call used to find the match; and a paged request is all-or-nothing, so a Console-side source failure is a 502, or a 503 when ClickHouse refused the query for resources, rather than a partial answer at exit 0. A --cursor request answered without the paging fields reached a Console that does not page: a node not yet updated while a deploy rolls out, or a Console that no longer pages searches. It ignored the cursor, so the CLI exits 3 with stage: "paging_unsupported" rather than hand back its newest rows as the next page. Retry after a short wait; if it persists, restart the walk without --cursor. Each page is a full search on the Console, run again from the cursor, so a walk costs about one search per page: walk with --limit 500, the Console's cap, to make fewer calls. A clause-only search (a clause flag such as --object, --field, --request, --response, --status or --trace-type, and no --text) reaches up to --limit candidates per call — 100 by default, 500 at most — where the whole capped answer of a Console before paging reached 5 000 per source; paging reaches the rest. The CLI follows no page on its own: it returns the page it was given, even an empty one with has_more: true, and a script loops. The CLI does not ask for the Console's whole-result totals (include_totals, which the counts and charts on the Console's instance tab and session page draw); to count a search's matches, walk its pages.
Model-call hits (--include-llm, 1.7.0). Opt-in: without the flag a search asks for none, and its request and answer are what they were before 1.7.0. With it, a free-text search (--text) also looks through model calls — text in their prompt or error message, or the whole of their call id, operation id, session id or gateway request id — and returns the ones it matches beside the operations, newest first with them, so calls take places on each page. The Console looks through model calls only in a free-text search, and a model call has no instance, user or key to scope it by, so the CLI refuses --include-llm without --text, with a clause flag (--trace-type, --status, --object, --field, --trace-id, --request, --response), and with an instance, user or key scope (--instance or a bound --instance-id / $XMEM_INSTANCE_ID, --user-id, --api-key-id): each of those would answer with no model call whatever matched. --session-id and --hours-back work with it. A model call carries its prompt and error, so the Console serves these hits to a caller with no instance restriction only — a super admin's key — and leaves them out for every other credential rather than refuse the search: a member's key gets the same operations it gets without the flag, and no model-call hits. auth status says whether this credential is a super admin's. Each hit names its call: trace call <llm_call_id> opens it whole, and trace get <trace_id> the operation it belongs to.
LLM calls of a session (1.6.0). The list holds the calls recorded under that session; a call whose session was not recorded with it is not listed, so treat the list as the session's recorded calls, not a guaranteed complete count. The API records each call's session with the call (a session over 256 characters only best-effort, through the Console's lookup by operation); a per-step benchmark call is listed only when its runner sent a session with it, and a schema generation or instance creation call only when its operation was recorded with a session. trace calls pages exactly like trace ls --search: follow has_more, pass the three next_before_* fields back as --cursor. On the last page the Console sets truncated: true when calls matching the filters exist before the --hours-back window, and the CLI warns (stderr, and the JSON document's warnings array) — widen the window, or pass 0 for everything kept. The older text fields (sub_stage, model_type, provider) read "" when nothing reported them, as in trace get; every newer one (instance_id, model_id, provider_type, finish_reason, reissue_of_llm_call_id, reissue_reason, schema_property_order, applied_temperature, applied_thinking, applied_effort, prompt_family, prompt_generator, prompt_schema_provider, prompt_version) is null then, so select(.reissue_of_llm_call_id != null) keeps only re-issues, as it does on trace get. The counts, times and outcome flags every call has (time_taken_ms, the token counts, is_success, is_refusal, is_cached) are always numbers and booleans; a setting or count only some calls report (max_tokens, temperature, no_cache, client_attempts, cache_read_tokens, cache_write_tokens), error_message and gateway_request_id are null when nothing reported them, and so, in trace call, are session_id, json_schema, result, raw_result (null for every reply the gateway served as written) and rejected_attempts. These commands need a Console that serves them: an older one does not accept a key on these paths and answers 401, which the CLI reports as exit 4 auth.
Two document shapes. trace ls returns the Operations-tab document; trace ls --search returns the Inspect document (above). They differ because the Console's two backends differ and this CLI does not reshape what the Console serves. Both carry the same identifiers per row (trace_id, instance_id, session_id, user_id, api_key_id, status), which is what trace get needs next.
Every operation row carries its internal ids. operations[] rows have operation_type, trace_id, instance_id, timestamp, status, is_success, error_code (super admins only: it is the server's own cause code, finer than the API's error codes), session_id, user_id, user_email, api_key_id, api_key_name, api_key_prefix, time_taken_ms, text_snippet, object_names, field_names.
Three of those never resolve for an API key, super admin or not, and this is by design rather than a gap.
user_emailis always absent: the accounts/userslookup is closed to keys (an agent may learn who it is, never enumerate the organisation's users), so rows keepuser_idand you resolve names yourself if you need them — and the Console refuses a key'sUser:search clause naming a whole address (User:sarah@example.com) with a400user_email_filter_unsupported_for_api_key; filter byuser_idinstead. For that reason--user-idrefuses a value containing@as a usage error (exit 2) on bothtrace lsandtrace ls --search, rather than sending a filter no key can resolve.api_key_name/api_key_prefixresolve only for the caller's own keys, becauseGET /api-keysscopes a key caller to its owner's keys. So a super admin's key does not see literally everything its owner's browser sees: it sees the same rows and the same fields, with those three enrichments empty. Everything scope-bearing — which instances, which detail fields,llm_calls, xuid substitution — is identical. Detail documents add what the Console's pane shows:source_id,write_mode/read_mode,scope,extracted_objects(an array holding one{objects, relations}document, failed writes included; empty when no extracted objects reached the journal: a write that failed before extraction finished or extracted nothing, or one that timed out),diff_plan(sanitised unless super admin),written_objects,migration_id,proposal_version,schema_version,stage,triggered_evolution {migration_id, evolution_trace_id, update_trace_id},sql_queries(the rows owned by the read's instance, for every caller who may open the read), and two tiers of gated fields. Super admin only — the accounts API decides, for a key as for a browser session (a key counts only when its owner and its creator are both active super admins):llm_calls[](each model call the operation made; fields below),step_decisions[](what each step of the operation decided, per item; below),full_error_message, the write's and read's cause codeerror_code, raw token counts, and unsanitised xuids. Callers with no instance restriction at all — a super admin, or a browser session on aCONSOLE_LOCALConsole; never a scoped key:ddl_queries,schema_generation, and the ownerless rows ofsql_queries.
Each llm_calls[] entry, oldest first, is a call made under the operation's id that names the document's instance, or names none (calls recorded before the API sent one, and work that runs for no instance, such as a schema generation): trace ids are not unique, so another instance's operation can share the id. A call that names no instance carries names_no_instance: true, since it is listed by the operation id alone and may be that other operation's; a call that names the document's instance carries no such key. Its fields: llm_call_id; sub_stage (the pipeline stage that made the call); model_type (the model slot asked for) and provider (the one that served it); called_at; time_taken_ms; prompt_tokens, completion_tokens, reasoning_tokens (part of the completion, not added to it), total_tokens; is_cached, is_success, is_refusal, error_message, gateway_request_id; prompt, json_schema, result. Then what explains a call's outcome:
reissue_of_llm_call_idandreissue_reason: this call re-issues the earlier call with that id, which failed with that error code. A call sent to another model after it was refused, blocked for its content, or answered with replies that kept failing its schema, and the intent pipeline's verification call sent to its fallback model after a provider error; a reply cut at its output ceiling sent again with a higher one; on writes the same overflow sent to another model at the same ceiling; and the intent pipeline's operations call cut at its ceiling sent again to the same model at the same ceiling: all are re-issues.reissued_as_llm_call_idsis the other direction: the calls in the same list that re-issue this one. So either call leads to the other, with no second request.max_tokens,temperature,schema_property_order,no_cache: the settings the call requested, not necessarily what the model ran with: depending on the model and its settings, no temperature is sent at all.schema_property_orderis also null for a call sent without a schema.finish_reason: why the model stopped, in the provider's own words, not normalised.end_turn,stop,STOPandtool_useare normal stops;max_tokens,lengthorMAX_TOKENSmeans the reply hit its output ceiling, andmodel_context_window_exceededmeans the prompt and reply outgrew the context window. On a failure it is set where the model side reports it: always for those two, and for a refusal, a content filter or safety stop, or a schema miss after the model side's own retry where it reports those too; null otherwise. Read a refusal fromis_refusal. One exception to "the provider's words": a cached Gemini reply (is_cached: true) first stored before 2026-05-06 readsstopwhatever Gemini reported.rejected_attempts: the replies rejected before this call's answer or error (one that missed the schema, say), as an array; a recorded value that is not valid JSON is served as its text.model_idandprovider_type: the model id the slot pointed at for this call and its provider type (zai-org/GLM-5onnebius), named for this very call, whether it was answered fresh or from cache. A call refused before any model ran (a rate limit, say) still names the model its slot pointed at. A failed call names the model from the last answer that named one, and none when no attempt got such an answer (every attempt timed out or could not connect) or the call was cancelled. It is the model of that answer only: an earlier attempt's rejected replies may come from the model the slot pointed at before.model_typenames only the slot, which can be pointed at another model;model_idis the model id the slot pointed at when it answered, which for some models is a vendor alias rather than a dated snapshot. Null when the call did not record it, never guessed from the slot.client_attempts: how many attempts were made for this call, the one that answered or failed included; an attempt that could not connect counts too. It is the calling service's own count, not something the model side reports. Null for a call that was cancelled or stopped before its first attempt, and for calls made without the usual model client (description generation, for one).gateway_repairs: what was done to the reply before it was served, in a fixed order (not the order it happened in):repaired(fields written as JSON text were decoded),json_recovered(the first of several JSON values was kept),omitted_scaffolding:<field>(a reasoning field the reply left out),schema_not_enforced(no grammar held the reply to its schema),strict_fallback(a strict request was refused and a second, non-strict one answered) andanswered_in_text(the reply came as text, not as the tool call it was asked for); on a call the caller asked the gateway to hedge, alsohedged(a second copy of the call was sent) andhedge_served(that copy's answer was served). The last three of the first six say how the schema reached the model rather than that the reply was changed, and the hedge flags say how the answer was fetched, so a non-empty list does not by itself mean a repair. A fresh reply reports them, so on a fresh successful reply that names itsmodel_id,[]means none of these flags applied; on a cache hit or a call that names no model,[]means not reported. A failed call reports them where the model side reports what it did before the failure, so there[]means none applied or not reported. Re-encoding a reply (key order, whitespace, very large integers rounded) is never reported, andschema_not_enforcedrecords the model side's own choice, not a verified grammar.applied_temperature,applied_thinking,applied_effort: what the model side actually sent the provider for the attempt that answered, or on a failure its last attempt: the temperature as sent, the thinking mode (adaptive,enabled,disabled,level:<x>,budget:<n>) and the effort, ornonewhen it sent nothing for one;otherstands for a value outside the model side's fixed lists. They can differ from the requested settings: a slot that drops temperature, thinking turned off on the retry after a reply missed its schema. Null when not reported (a cache hit, a call that failed before reaching a model, or calls recorded before these fields existed).cache_read_tokens,cache_write_tokens: how much ofprompt_tokensthe provider read from and wrote to its prompt cache; parts ofprompt_tokens, never added to it. Null when none or not reported.prompt_generator,prompt_schema_provider,prompt_family,prompt_version: the prompt renderer the call's model slot resolved to when it was made: the two classes the slot's prompts and response schema are rendered with, asmodule.QualifiedName; the model family a Claude slot's prompts are picked by (null for other providers, whose prompts are picked per slot); and a 16-hex-digit version of the classes' source. The version changes whenever that source or any project module it imports changes, the model-call code included, so a new version does not by itself mean the prompt text changed; it never changes with the instance's schema. The version is null for a call the API made before it had computed it (the first moments after a restart, or after a repoint to a renderer no slot used before) or where it could not read the source. All four are null for a call that renders no prompt, for a call whose caller wrote the messages (a per-step benchmark call of purposejudge,extractorsynthesis, and the LLM-as-judge endpoint), and for calls recorded before the API sent them. Aprompt_evalcall names the renderer of the API node that served it, which during a deploy can differ from the one whosebenchmark_prompts/preparerendered its messages.raw_result: the reply as the model wrote it, where a repair or recovery (repaired,json_recovered) changed its value;resultholds the changed one. Null otherwise, and not reported on a cache hit or a failed call (a cache hit replays the repaired reply only).
A value the call did not record is null, and reissued_as_llm_call_ids and gateway_repairs are []; calls recorded before these fields existed read that way throughout.
Each step_decisions[] entry is one record of what one step of the operation decided, oldest first (by recorded_at, then sub_stage). A step records each time it runs and decides something (a step that decided nothing records nothing), so one operation can hold several records of one step, and every record is served; none is merged into another. A write's deletion check records in its own process and again where the diff engine applies its gate, and a write retried whole under the same trace id (a stale-schema retry, a stall requeue, a stuck write claimed again) records every step again. Writes, reads and schema evolution record today. A write's extraction records too, under extraction. steps named like its model calls (extraction.structured_output, extraction.description_merger, extraction.batch_field_extractor, extraction.field_verifier, extraction.relations_extractor, extraction.relations_verifier, extraction.deduplication): what code decided about a reply (candidates folded into one, a reply set aside so the extracted values stand, connections dropped, a candidate left out of the write, a group of types split), and the verifiers' own rejections. Field verification records once per object type, when that type's field processing ends; a write that fails before then records none for that type. When the judge in front of field verification is configured but does not run on a write whose detection found something, the write records why, once, under the stage the judge's calls would journal under (extraction.verification_judge, or shadow.extraction.verification_judge in shadow mode): one item, kind judge, decision not_run, with detail.not_run_reason (sampled_out, pinned_provider or config_unavailable) and detail.mode. Extraction's items have the diff engine's shape: kind is merge, object, relation, relation_type or type_group; decision is folded, skipped, not_held (the verifier found the text does not state the object holds, so it is marked as one that does not), kept_unverified, verifier_skipped (field verification did not run because the judge in front of it cleared the object), key_restored, rejected, uncastable, dropped, split or escalation_disabled; detail holds field names, candidate numbers and counts (candidate_count, candidate_numbers, kept_number, ignored, basis, filled_fields, conflicting_fields, relations_repointed, fields, nulled, omitted, connection, field, candidates_per_link, relations, types, halves, refused_max_tokens, error_code), and no field's value except an object's key: in key, in a dropped relation's links (Type(field='value') per link), and a description for an object that has no key. /extract records its extraction the same way; it has no detail document of its own, so its records show only on a write's document when that write, on the same instance, reuses its trace id. A write's apply records what its merges did to the stored rows, under write.merge_application, once the write commits (a write that rolls back records none): one item per merge action, kind merge, named by the surviving row (the diff engine's merge items are named by the row merged away instead): its object_type, its key (absent for a type without a key, for a key with any part NULL or missing, which could name another row, and when the two rows were one) and its xuid, with decision applied and, in detail, the row merged away (merged_away_xuid), relations_repointed, relations_dropped by reason (linking_the_merged_rows: a relation between the two merged rows; removed_by_this_write; duplicate: one the survivor already held) and filled_fields, the survivor's empty fields filled from the merged-away row, by name; or decision nothing_to_merge with why in reason (the two rows were one, or the row to merge away was already gone). Schema evolution records under operation_kind evolution: review, decide and apply each journal their steps' records once, when the stage ends, under their own trace, so an apply's show on its update document (its trace is the update id), and the detached pass that resolves an apply's gaps afterwards journals its own under the same trace. Its steps are the two model calls' names, gap analyzer (gaps never analysed or stored with no concepts, rows a reply left pending, concepts the parser dropped) and semantic gate (what the gate may do with each suggestion, candidates kept without a verdict, verdicts downgraded or not acted on), and the rule steps evolution.backlog, evolution.resolution_filter, evolution.clustering, evolution.consolidation, evolution.prior_decisions, evolution.prerequisites, evolution.evidence_retirement and evolution.apply; kind is gap (named by its feedback id in key and its concept's object and field), suggestion (its fingerprint in key, its change's names, and the gaps it was built from in detail.gaps, the first 20 with gaps_total when there are more), cluster, decision, backlog, reply_entry, build or gate, and no item carries what a user wrote. What a transaction did (a gap resolved, stored with no concepts, deleted or retired) is recorded only once it commits, and a row only when that step's own write or delete reached it. A build retried on a stale schema records both attempts: once the build runs again, every item the stage notes until it ends, the build's and the stage's own after it, carries detail.attempt (2), so an item without attempt was noted before the build ran again, and a retried item under evolution.consolidation records that it did; an omitted item is a marker, not a decision, and carries no attempt. A read records what the reader's own rules decided, under the name of the model call whose reply a decision is about (read.question_decomposer, read.sql_syntax_fixer, read.empty_result_reviewer, read.overfetch_reviewer, read.answer_formatter) or under a rule step (read.scope, read.vector_grounding, read.sql_rewrites, read.sql_guard, read.sql_retries, read.answer, and read.other for a family no step claims yet); a decision about a SQL statement a model call wrote goes under read.sql_rewrites, with the calling step in detail.phase where the rule names it. A read step that decided more than 101 times keeps its first and last 50 decisions, with one item (decision omitted, detail.count) where the rest were left out, cut further from the middle when they do not fit one record. A read journals its records once, when it ends, so a read still running has none yet, and a read retried on a stale schema runs again under the same trace id and records every step again; its items have kind (the decision family, such as sql_guard_refused or distinct_order_by_case_dropped), decision (applied or not_applied), reason where the rule says why, and detail.part, the part of a decomposed question the decision was made for, counted from 1, where it was made for one. sub_stage names the step in the llm_calls[].sub_stage vocabulary, so a step's decisions and its model calls join on it (a re-issued call journals under its step's name with a suffix such as .refusal_fallback, so it joins on the name as a prefix; the reader's rule steps, extraction.deduplication and write.merge_application have no model calls of their own) (diff_engine.keyless_binding, diff_engine.deletion_check, diff_engine.intent_rules, diff_engine.value_span_containment, diff_engine.intent_verification_deep, diff_engine.alias_confirmation, diff_engine.object_resolution, diff_engine.unwritten_identity_verification, diff_engine.plan_construction, the intent pipeline's diff_engine.intent_gate, diff_engine.intent_operations, diff_engine.operations_repair and diff_engine.operations_verification, and the read. steps above). A model call made in shadow mode, beside the work it never changes and never charged, carries the prefix shadow. on its step's name; the intent pipeline and the field verifier's judge are the steps that run in shadow today. The field verifier's judge, which can stand in front of extraction.field_verifier on a DEEP write or /extract, makes its calls under extraction.verification_judge, or shadow.extraction.verification_judge in shadow mode, and records under that same stage, once per object type, one item per object it was asked about: kind object, decision flagged (a field at or over its threshold, or one no question covered), cleared or not_judged (no verdict, which counts as every field flagged), with detail.field_scores (the flagged fields the judge scored, and their scores), detail.unjudged_fields (flagged fields no question covered), detail.score, detail.field and detail.question (the top score and where it came from), detail.threshold, detail.questions_asked and detail.verifier (ran, ran on the flagged fields and the key, or skipped). In on mode the verifier is asked only about the flagged fields and the key; in shadow mode it sees every field, and the item says what on mode would have sent it. A verifier_skipped item under extraction.field_verifier is an object an extraction.verification_judge call of the same operation cleared; every question and answer is in that call in llm_calls[]. The intent pipeline names its model calls by its step names above, with the prefix shadow. in shadow mode (diff_engine.operations_repair the operations step asked once more about the entries its checks dropped); diff_engine.intent_operations records what the write did with the answer in on mode only, where it stands in for diff_engine.intent_rules, and in either mode (with the prefix in shadow mode), once the run has finished, one item when the operations call ran out of its output budget and was asked once more: kind intent_operations, decision retry_answered or retry_failed, and detail.model, detail.error (the first call's code) and, on retry_failed, detail.failure (the type of the error the step then failed with); a run the write's grace cancelled with the retry in flight, or one whose gate closed or failed, records none, and the retried call is the step's llm_calls[] entry whose reissue_reason is provider_output_token_limit_exceeded. diff_engine.operations_repair (with the prefix in shadow mode) records one item, once the run has finished, when the operations step asked its model once more about the entries its checks dropped: kind intent_operations, decision repaired (the second reply stood), repair_rejected (it was not the first reply with those entries fixed, so the first stood with its drops) or repair_failed (the repair met an error, so the first reply stood with its drops), and detail.model (the model the repair asked last: the one that gave the first reply, or its fallback after an outage) and, on repair_failed, detail.failure (the type of the error it met); a run whose gate closed records none, and so does a reply over the cap, which is never repaired: the write falls back to the engine. diff_engine.intent_gate (with the prefix in shadow mode) records one item when the gate's deadline, the write's grace, opened it: kind intent_gate, decision opened_by_deadline, and detail.deadline_seconds, detail.unanswered_calls (the gate calls cut off) and detail.sentence_count. A step whose decisions act on another step's calls names itself the same way: diff_engine.intent_rules acts on the replies under diff_engine.object_and_relations_deletion_detection and diff_engine.batch_field_erasure_detection. The records hold what the engine decided that the operation's llm_calls[] (their prompts and replies) and its diff_plan do not already show, so the model's own answers are read in llm_calls[], not here. decision_count is the step's true total and decisions_truncated marks a record cut to fit (for a read step, also one cut to its first and last 50 decisions), so decisions can hold fewer items than the count. decisions is the items as the step recorded them, a JSON array, or null when the stored text is not one (the count still shows). A pane serves at most 500 records and 4 MiB of decisions text, the newest; when it cut older ones it adds step_decisions_truncated: true beside the array, and otherwise the key is absent. A trace id a client reuses across writes serves every write's records together, ordered by time with nothing between the writes. The diff engine's items share one shape: kind (what the item is: intent_gate, intent_operations, intent_verification, object, identity_change, merge, filtered_deletion, filtered_update, relation, deletion, alias, relabel, scope, detection, operation, intent_pipeline) and decision (what was decided: deletion_dropped, converted, rejected, kept, bound, not_bound, matched, left_out, …), then, where set, object_type and key (the primary-key values as field='value'), index (the object's position in the diff engine's sorted object list, not in extracted_objects[]), xuid (the stored row), reason, and detail (anything else the step decided). diff_engine.keyless_binding records one object item per record of a keyed type that states no key but another field: bound to the one stored row it names (its key and xuid), or not_bound with why in detail.outcome (a record one stored row matches in every field it states carries that row's key and xuid when it is left not_identifying, matching only in yes/no and listed-value fields and never put to the verifier, or rejected or unverified, the verifier not confirming the text refers to it); same_key_group (the write holds records of different types with the same key, so nothing of it is looked up), key_stated_for_another_type (a record of another type in the write states the key of the row it would bind to), key_of_another_type (a stored row of another type has that key) and key_check_unread (the stored rows could not be read, or the key has more fields than the check looks up) are a temporary net against extraction copying a record's identifier onto another type; a binding left unbound for one of the last three carries the row it would have bound to (its key and xuid; a record not asked about its closest rows for them lists those rows in detail.other_type_rows instead), and the other types in detail.other_types: for key_stated_for_another_type and key_of_another_type, and for a record set aside unasked as key_check_unread whose rows stand down for different reasons, the types its rows' keys were found under. The same-key groups and the stated-key check go once extraction no longer returns such copies; the stored-key check goes only once the copies earlier writes stored are cleaned up too, or a scan finds none. A stored copy whose key differs only in case, surrounding spaces or accents is not found. In on mode, Phase 1's record_where lookup may also ask the verifier under diff_engine.keyless_binding (on a Claude 5 model, when one stored row matches and the answer would be used once it is confirmed), about a rename's or a merge's record the text names by its fields whose extracted record carries the operation's new key, and records no item of its own: what came of it shows under diff_engine.intent_operations, where a bound rename is named by the stored row's key, or as record_where_unbound with detail.sub stated_key, or as the fallback a bound answer met later (such as rename_old_key_unmatched, or rename_or_merge_rejected when Phase 1.5 did not confirm every rename and merge of the answer); under intent_pipeline_failures: refuse a bound answer whose translation fails, or whose key-only lookup could not run, is refused instead (a failure of the verified relabel's own work, relabel_failed, still goes to the engine). In on mode diff_engine.intent_operations says what the write did with the intent pipeline's answer: an operation item per operation it applied, its decision the operation's kind (delete, unlink, unlink_all, move, clear, rename, merge, bulk_delete, bulk_update) and its reason the passage that asks for it, then not_applied for one the write could not carry out (a delete of a record by the new name a rename of the same write gives it reads "it is also the target of a rename", as the engine's own rule says it) and dropped for one the pipeline dropped, each with why and detail.position (its place in the model's reply), then an object item skip for each record of a keyed type that states no key and that the write skipped, and erase_refused for each record bound to a stored row by its other fields whose clears were not applied (detail.fields); a clear item therefore names what the pipeline asked for, not what was written. When the engine's own detection decides the write instead, the step records one intent_pipeline item, decision engine_decides, whose detail.fallback names why (its reason says it in words) and beside which the engine's own steps record as with the pipeline off: missing (no result reached the write), unreadable, translation (the rows the operations name could not be read), dropped (the pipeline dropped an operation it proposed for a reason other than its verifier's rejection, so its answer is not the whole change), verifier_rejected (a temporary net: the pipeline's verifier rejected a delete, a clear, an unlink, an unlink_all or a move it proposed, which may be about how the operation names its records rather than the change; a rejected bulk delete or update does not count, and a rename it rejects, or a merge while execution.entity_merge is on, goes to the engine as rename_or_merge), record_where_unbound (it names a record by the field values the text states, a key stated in part among them, and once verified, binding it through the write's own extraction found no single record for it; a writer that predates the binding decided it before the pipeline's verifier was asked), unresolved (it saw a change whose records it could not name: a record described rather than named, records selected through a relation, some but not all links of a kind, or all of them handed over to another record; every one of them ending, but those the text keeps, is an unlink_all), rename_or_merge (it holds a rename or an unlink_all sharing a record with a merge, renames that swap, cycle, fork or converge, or an unlink_all whose record another operation names in its relation, decided before the pipeline's verifier is asked, or the verifier rejected a rename, or a merge while merges are on), rename_old_key_unmatched (it renames a record that no single stored record has by the name the text gives), merge_loser_unmatched (it merges away a record that no single stored record has by the name the text gives), rename_onto_stored (it renames a record onto a name another stored record already has), rename_record_partly_stated (the write states a record without the rest of a key a rename names, so whether it is that rename's old record, its new record or another one is unknown), clear_in_question, unlink_in_question, move_in_question, repoint_in_question (temporary nets: while the text holds a question mark, it clears a field, unlinks records of a relation type the extraction holds a relation of, or moves a relation, or, whatever it holds, the extraction holds a relation of a type keyed on some of its ends but not all, which written re-points the stored link those ends share, as with the pipeline off; Phase 1.5 cannot verify or take back any of these), delete_with_values (it deletes a record the write's own extraction gives values other than its fields' defaults), unlink_replaced (it unlinks records while the write's own extraction holds another record the link may have moved to, which no new link joins to the unlink's other ends and no other operation ends or removes), unlink_all_with_links (it ends every link of a kind that a record has, while the write's own extraction links that record by that kind to a record it does not keep, or holds another record of its type that nothing accounts for, as a transfer the answer misread would), unlink_all_names_an_end (the extraction holds a record of the kind an unlink_all ends that it does not keep, as when the text names the one link it ends, or the unlink_all keeps a record at only some of the roles its type takes), key_rewritten (an operation's key was read as the extraction's spelling), unmatched_key_only (the gate opened, while the extraction holds a record by its key alone that the answer would write and no stored row has; a delete's record, a rename's old and new records, a merge's survivor, a move's new end and a record an unlink_all keeps are not looked up), key_only_lookup_failed (the same, but whether those records are stored could not be read), end_not_stored (an unlink's end, an unlink_all's own record, or a move's old or kept end, binds no single stored row: none has its key, or several do, so the stored link would stay), kept_record_not_stored (a record an unlink_all keeps binds no single stored row, so its link could not be told from the others and could end; a record the write creates counts too when the unlink_all would end a stored link, which could be that record under another spelling), kept_link_missing (a record an unlink_all keeps has no link to the unlink_all's record, stored or in the write, so the record would be left with no link of the kind), unlink_all_partial_fetch (an unlink_all's record's links were read from a fetch cut short, so the links not read would stay), rename_or_merge_rejected (the write's second verification did not confirm every rename and merge of the pipeline's answer, so the engine's own detection decided it again from the start; a temporary safety net, until the pipeline binds the records its operations name itself; it goes together with unmatched_key_only and the end guard, which would otherwise send most such writes to the engine), end_not_extracted (a move's new end is neither a stored row of its type nor a record the write's extraction holds, by its key: a key the pipeline made up, such as a name or part of an id), empty_answer_check_found_intent (a temporary net: the answer holds no operation while Phase 0's gate, which read the deletion check the write ran, is open other than by its bulk-update or merge verdict alone), date_field (an operation names a field in which the write's extraction resolved a date token, or dropped one that named no day, which the pipeline does not yet state as the extraction resolves it; a temporary safety net, until the pipeline resolves those dates too), inside_value (the answer holds an operation beside a value the text assigns to a record's field, a long one quoted verbatim or any one an operation's quote touches, which may narrate changes the caller did not ask for, or the check could not tell, so the engine's own detection decides the write), or the step a run without an answer stopped at (gate, operations, verification, executor, late, not_run). A write of an instance that pins its write text to a provider is no fallback: its instance's own mode is off, so the step records one intent_pipeline item, decision instance_mode, with detail.mode off and detail.sub pinned_provider, and the engine's own steps record beside it as with the pipeline off. Beside fallback, detail.sub gives why as one code with no value, when one is known (for unmatched_key_only what the records were, relation_end, not_an_end, partial_key or empty_answer; a failed stage's exception type, a not-run reason, the drop kinds and reasons, the rejected kinds, whether rename_or_merge was decided before or after verification), detail.dropped_operations lists each operation the pipeline dropped (position in the model's reply, operation kind when readable, reason, and part, a code for what within the reason failed, when known), and detail.unresolved_changes each change it could not name the records of (position, evidence, the passage that asks for it, object_type when the model gave one, and shape, a code, when the model gave one). dropped_operations carries no field values; an unresolved_changes entry's evidence is a passage of the write's own text, as an operation item's reason is. diff_engine.intent_rules logs what the engine's rules did to the detection model's answer, in the order they acted, so an item can be dropped and later restored (a rename whose old record is stated by part of a composite key is an identity_change item completed, bound to the one stored row its stated part matches and named by that row's xuid, or not_bound, left as stated so the write goes as it would without the step: no stored row or several match, the one row disagrees with the new record, a stored row with a NULL or blank key part matches, the database could not be asked, a value is not one its field can hold, the new record is of another type than the rename's, no index serves a lookup by the stated part, another rename or a merge lands on the same new record, or something else in the write may name the row or the key, its kind in detail.named_by); diff_engine.plan_construction says what building the plan decided after every earlier step, which the plan shows only by leaving it out (a merge the relation-budget re-check refused or re-admitted after alias binding, a deletion a rename overrides, an unlink dropped for a row a confirmed delete does not run on or a lookalike row the write does not bind, a move whose old link stays with the replacement guard's cause, a dropped merge or one already a single row, what a scoped write left out). A deletion that verification rejected reads kind: "deletion", decision: "rejected" under diff_engine.intent_verification_deep, with what the object became and why; the proposal itself is the detection model's reply in llm_calls[]. Another part of the system may record items of its own shape here; they are served as recorded. Every detail pane serves its operation's records the same way; the write, read and evolution panes serve them for an operation still running or stale too (create and update have no such pane). A step that refuses the write still records what it decided first: the detector its rules, resolution what it found, plan construction the merges, unlinks and scope it changed. A caller who is not a super admin gets neither step_decisions nor step_decisions_truncated, exactly as for llm_calls[].
A scoped key gets [] for ddl_queries / schema_generation, not the rows. Those two come from records that carry no instance ownership — the schema generation's trace id is even client-supplied — so they cannot be scoped to an instance and are served only to callers with no instance restriction at all. This is a deliberate fail-closed choice, not a bug to work around: an empty array means "not available to this credential", never "this operation ran none". llm_calls[] behaves the same way (gated on super admin) and always has. sql_queries is split: statements recorded with their owning instance reach every caller who may open the read, even when another instance reused the trace id, while statements recorded before ownership was tracked carry no owner and reach unrestricted callers only. A scoped key therefore sees [] for reads that old. To let a script tell the two apart, the Console sets a sibling boolean next to each — sql_queries_withheld, ddl_queries_withheld, schema_generation_withheld — that is true exactly when a row that exists was withheld from this caller: for ddl_queries / schema_generation that is every scoped caller, for sql_queries a scoped caller on a read that has ownerless rows. So [] with …_withheld: false is "none recorded", [] with …_withheld: true is "not yours to see". Xuids are hidden for every non-super-admin, including on writes that carry no identity map — the substitution is done by the Console, server-side, so a caller with no browser sees #hidden rather than a raw id.
Who sees what — the Console decides; auth status tells you which view to expect.
- A regular key sees the operations of the instances the accounts API lists for it — the same set
org list instancesprints. That is at most what its owner sees in the Console, never more. - Access requires the key's role to carry
data.read— the same permission the data-read endpoint requires. A role deliberately scoped away from data (auth statusshows the codes underpermissions) is refused with 403 → exit 3, stagepermission, whoever owns the key — a permission denial, not a bad credential: rotating or re-issuing the key cannot fix a role that was scoped this way on purpose. An unknown or missing key is the separate 401 → exit 4 (auth). - A key owned by an active super admin and created by one sees the super-admin Console: every organisation's instances, no instance filter, and the super-admin-only detail fields above. A key an organisation's Owner created for a super admin (an Owner may create keys for its members) is scoped like any other key. The accounts
/whoamiis_super_admindecides — the key sees the same rows and the same scope-bearing fields its owner's browser session sees, minus the three enrichments no key resolves (user_email, andapi_key_name/api_key_prefixfor other people's keys; see the note above).auth statusreports it assuper_admin. - When the Console cannot work out that scope — its accounts API is unreachable, answers non-2xx, is undecodable, or is not configured — it answers 503 with
{"error": "instance_scope_unresolved", "reason": "accounts_…"}(oraccounts_unavailablewhen the key's own lookup failed the same way) instead of an empty document. The CLI reports that as exit 3, stageunavailable, with a message that says the scope could not be resolved and that this is not "no operations": a zero-row answer from a Console that could not decide would have read as a quiet instance. - No new permission is involved: the Console answers a key as it would answer its owner's browser session, narrowed to the key's instances, and treats it as a super admin's only when its owner and its creator are both active super admins. It never mints a session for a key. Filters that need to look other users up (
User:-style email filters) are not offered: an API key can identify only itself, never list or look up users — filter by--user-id.
The Console origin. trace … talk to the Console, a second origin. It is --console-url → $XMEM_CONSOLE_URL → inferred: https://console.xmemory.ai for the default API, the /console sibling of a /xmem base, https://console.stg.xmemory.ai / https://console.pp.xmemory.ai for the stg / pp APIs, :8002 for a local :8000. A key bound to any other API origin gets a usage error (exit 2) rather than a guess — the credential-binding rule holds across origins.
Parity. These commands are the Console's data path, not a copy of it. If the Console gains a filter or a field, it is added to the same list here and is available; the MCP server exposing the same data is deferred and will follow the same rule (see the note in the MCP server source).
Auth & meta
| Command | Description |
|---|---|
auth login |
PKCE via Console /xmemcli/<challenge> → .xmemrc.json. --auto-approve (1.7.4+: the same page opened with ?auto_approve=1&host=<hostname>; once the browser holds a Console session the Console hands the CLI a code with no click, and a key named CLI auto-approved login (<hostname>, <timestamp>) is minted when the CLI redeems it at /cli/token, once per login; refused beside --email; the payload carries auto_approve: true), --no-browser, --timeout, --console-url, --callback-port (pins the loopback callback port for ssh -L; 0 or omitted means any free port, otherwise 1024–65535; also $XMEM_CALLBACK_PORT, which is read globally). An explicitly named Console (--console-url, $XMEM_CONSOLE_URL, or the one pinned by a single-origin URL) is cross-checked against the API origin before the browser opens or a pasted key is sent anywhere — a provably mismatched pair (mixed loopback-ness, a production half paired with a non-production one, or a stg / pp half paired with anything but its own origin; a single-origin /console beside its own /xmem on one origin is one deployment, even on a stg or pp host, while the production halves are still held to their defaults) is a usage error (exit 2), on the interactive paste path as much as on the browser path. When the API comes from the rc: an origin that is neither https nor loopback (localhost, 127.0.0.1, [::1]) is refused (naming a bare origin with --api-url beside an https --console-url accepts it), and if that API names its own Console (a /xmem base its /console, a local :8000 its :8002, stg / pp their table Console), a named Console must be that one, in any spelling of that origin (case, a default port, trailing dots on a named host, localhost / 127.0.0.1 / [::1] for a loopback one) but on the same mount — any other is refused (exit 2), so a $XMEM_CONSOLE_URL exported for one deployment cannot mint a key into the rc of a deployment whose Console is known. Naming the API on the call makes the pair the caller's: --api-url with the Console in --console-url, or $XMEM_API_URL with it in --console-url or $XMEM_CONSOLE_URL. With no --api-url, $XMEM_API_URL or positional URL, the API origin is the api_url of the nearest .xmemrc.json (see the 1.7.1 note below), and both the browser and the --email path print that origin and the file it came from before anything is sent — except for the production default, where nothing is printed. With --email ADDR (+ optional --org-name, used only when a new account is created; requires --email): headless email sign-in — one emailed approval, then the CLI mints its own org-wide key named CLI email login (<hostname>, <timestamp>); details in the auth-flow reference. New-organisation creation additionally requires the deployment to allow public registration. Payload shapes: a fresh email mint carries method: email, key_name, api_role, and org_created; the browser path carries method: pkce (no role/org fields); a matching --api-key or rc credential short-circuits to status: already_authorized with source: flag / rc (persisted: false on the flag arm, which saves nothing); a matching $XMEM_API_KEY is copied into the rc and reports status: authorized, source: environment. Exit codes follow the standard HTTP contract (401 → 4 with stage auth, 403 → 3 with stage permission, other HTTP/network/server-state failures → 3). |
auth logout |
Remove active .xmemrc.json |
auth status |
Call /whoami. No key → exit 0; bad key → auth error; good key → email + prefix + super_admin (whether the key is a super admin's, meaning its owner and its creator are both active super admins — what decides which Console view trace … return) + permissions (the key's own capability codes; trace … requires data.read among them). A Console named in $XMEM_CONSOLE_URL is cross-checked against the API origin before the key is sent to it (see the 1.7.1 note below); a mismatched one exits 2. |
mcp <instance-id> |
Serve one instance to an MCP client over stdio, using this CLI's credential. Not for humans — see below. |
version |
CLI release version (no network) |
status |
Local health: version + whether .xmemrc.json exists, and the mcp_url it declares when it declares one (no network) |
mcp is a transport, not a command you run. An MCP client starts it and speaks
JSON-RPC to it over stdio; it forwards each frame to <mcp-url>/instance/<id> with this
CLI's credential attached, and writes the answer back. The Console renders the
registration as claude mcp add <name> -- xmemcli mcp <instance-id> (with
--mcp-url <origin> appended when the MCP origin is not the client's own default), or the
equivalent for another client — replace the bare xmemcli with its absolute path, in
double quotes. The client stores the command as written and resolves it against its own
PATH every time it starts the server, and that PATH need not carry the directory the
tool was installed into; registered bare, it fails there — Claude Code reports
ENOENT: Executable not found in $PATH: "xmemcli". command -v xmemcli prints the path on
macOS and Linux, (Get-Command xmemcli).Source in PowerShell on Windows. If the bare name
is registered already, remove that server entry before adding it again: Claude Code refuses
mcp add for a name that already exists rather than replacing it.
It exists because an MCP client can reference an environment variable in an
Authorization header but cannot read .xmemrc.json. Reading the credential per
connection means no credential is captured when the server is registered, so a
configuration written today still works in a session opened next week with an empty
environment.
Where a file-held key may be sent. The MCP origin is configured separately from the API
origin, and a project .mcp.json arrives by git clone — it controls that server's args and
env, so it is not allowed to vouch for itself. A key read from .xmemrc.json therefore reaches
only the MCP origin that same file records in mcp_url, the origin paired with its api_url in
this client's built-in table of shipped deployments, or a loopback host when both ends are on this
machine. Anywhere else needs a key named on the call with --api-key.
A recorded origin says where, never how: a remote one must be https, so a hand-written
http:// entry is refused rather than sending the key in clear text. Loopback stays exempt — those
bytes never leave the machine.
The mount path is part of the destination, not decoration. A deployment serving every route
group on one hostname puts MCP at https://host/mcp, the REST API at https://host/xmem and the
OAuth server at https://host/oauth2; an rc recording the first authorises the first only.
auth login fills in mcp_url from what the API reports about itself, which is what makes an
on-premise deployment work: its MCP host is in no table this client was built with, and every
attempt to derive one host from the other has been wrong in a new way. If the transport refuses
an origin you expect it to accept, run auth login against that deployment again — the rc predates
the field, or that server does not report one. That works even when the stored key is still good:
the --email path records the origin it learns while checking, and reports it as mcp_url on the
already_authorized payload. A deployment that has stopped serving MCP answers null, and the
recorded origin is dropped rather than left authorised — and if that removal cannot be written,
the command fails rather than reporting success over a host that is still authorised.
Two consequences worth knowing:
- stdout is the protocol. Alone among these commands it emits no JSON document and
honours neither
--jsonnor the exit-code table above; its exit code is a process status. Diagnostics go to stderr. - Signed out is reported, not fatal. Every request is answered with a JSON-RPC error
naming
auth login, because a client that is told only "the server failed to start" gives the reader nothing to act on. Exit code and stage do not apply.
Console /xmemcli routing:
- Onboarding → silent onboarding-key handoff to the CLI (no overlay, no button click).
- Post-onboarding → API Keys create modal → “Use this key in the CLI”.
Quota (read-only)
| Command | Description |
|---|---|
quota |
Usage / limit / window start for the key's cluster (derived from instance → cluster). |
- Default: exit
0when quota is readable; stderr warning when usage is high. --fail-if-under THRESHOLD— exit 7 when remaining quota is below that share of the limit (0.1or10%). Distinct from exit 6 (API quota exhausted). Seexmemcli help quota.
Quota increases are Console-only — see What xmemcli does not do.
Exit codes
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (bad flags, unknown help topic, missing required args) |
| 3 | HTTP / request failure — see HTTP status mapping (includes permission denied, other API errors, and unwritable -o paths) |
| 4 | Auth error — invalid or missing API key (401; stage: "auth") |
| 5 | Timeout |
| 6 | Quota exhausted (API quota-exceeded response; stage: "quota") |
| 7 | Quota headroom below --fail-if-under |
| 8 | Write still processing — the API's wait window expired while the write kept running (HTTP 200 envelope; stage: "processing"). Not a failure: poll write-status, never retry |
| 130 | Interrupted (Ctrl+C) |
HTTP status → exit code and JSON stage
xmemcli mirrors the API's 401 vs 403 distinction on the process exit code and on the machine-readable stage field. This is the single contract for every command that performs an HTTP call (read/write, org list *, schema/XMD, quota, auth status, …) — with one deliberate exception, below.
context is exempt, by design — from the release that introduces context, which is the
first one where this carve-out means anything. It is the one command nobody invokes: a
session-start hook runs it unattended, and a non-zero exit there costs the user their session
rather than their context. So every HTTP outcome — 401 and 403 included — exits 0 with an
empty context and an explanatory warnings[] entry. Use auth status to tell a credential
problem apart from an empty binding; context will not.
The exemption goes further than HTTP status. Any runtime failure inside context — a malformed
binding, an unreadable response shape, a timeout, a bug nobody anticipated — exits 0 with an
empty pack and a warning: line naming the cause. This is enforced in code rather than by
enumerating failure modes, so an unforeseen one degrades like the rest.
And it is exempt from the one-JSON-document rule on stdout. Every other command emits a JSON
error document in machine mode, including on usage errors. A piped, non---json context whose
arguments fail to parse writes zero bytes to stdout and puts its reason on stderr instead,
because a hook discards stdout at exit 2 — so a JSON error document there is a session start
failing with no stated cause anywhere the user can see it. Usage and parse errors are the only
paths that still exit 2; they are a mistake in the hook's own configuration, not a runtime
condition, and the hook author is the one reading stderr.
Quick reference
| API HTTP status | Shell exit code | JSON stage |
Meaning |
|---|---|---|---|
| 401 | 4 | auth |
Bad credential — missing, invalid, expired, or inactive API key |
| 403 | 3 | permission |
Bad authorization — key is valid but this key/role cannot perform the operation |
| Other 4xx/5xx | 3 | request |
Request failed for another reason (404, 422, 5xx, …) |
| 402 (quota exhausted) | 6 | quota |
Quota window exhausted — human must extend quota in Console |
any status with errors[0].code == WRITE_STILL_PROCESSING |
8 | processing |
Write is still running — the write did not fail. Matched on the code, whatever the status: a keepalive-flattened 200 and an unflattened 500 both exit 8, so this row overrides the 4xx/5xx row above. Poll write-status <write_id>; a retry starts a second write |
503 with body {"error": "instance_scope_unresolved" | "accounts_unavailable", "reason": …} |
3 | unavailable |
The Console could not resolve what the key may see (its accounts API is unreachable, non-2xx, undecodable, or not configured). Not "no operations" and not a bad credential — nothing was listed or checked; retry once accounts recovers. Recognised on the body, so it is named the same on every command that meets it. |
200 to trace ls --search --cursor … with no has_more |
3 | paging_unsupported |
The Console ignored the cursor and answered with its newest rows, so the answer is not the next page: a node not yet updated while a Console deploy rolls out, or a Console that no longer pages searches. Retry after a short wait; if it persists, restart the walk without --cursor. |
How to interpret failures
- Exit 4 /
stage: "auth"/ HTTP 401 → fix the key: login again, rotate the key, check$XMEM_API_KEY/.xmemrc.json, confirm--api-urlpoints at the environment that issued the key. - Exit 3 /
stage: "permission"/ HTTP 403 → the key works, but the operation needs a broader API role (for exampledata.write,instance.generate_schema,cluster.get_own). Do not treat this as a wrong password. - Exit 3 /
stage: "request"→ other HTTP failure (instance not found, validation error, server error). Read the error message and HTTP status in the JSON body.
Some commands attach a more specific stage (validate, usage, limit, not_found for trace get and trace call, …) while still using exit 3 unless the row above applies. write adds processing, which is in the table above and exits 8 rather than 3. The schema suggestions commands add their own stages: stale_proposal (re-run review for a fresh proposal_version), invalid_decision, dependency (accept the dangling dependencies first), not_initialised (submit a write first), and apply; review reports an evolution_in_progress condition as a successful status with exit 0.
Envelope errors (HTTP 200 with non-empty errors[]) are not HTTP 401/403; they typically exit 3 with stage: "request". Two exceptions. QUOTA_EXCEEDED exits 6 with stage: "quota", the same as it does on a real HTTP 402 — the keepalive flattening does not change the exit code — and this applies to every command that classifies the error, not just write and read. WRITE_STILL_PROCESSING exits 8 with stage: "processing" and is not a failure at all; unlike the quota rung this one is write-only, because its guidance is to poll write-status, which is meaningless for any other verb — elsewhere it falls through to 3/request.
Known bug. Some subcommands in the
instanceandschemagroups —instance getandschema getamong them — unwrap the response outside their error handling, so an envelope error never reaches the classifier and escapes as an uncaught exception: a traceback and shell exit 1, which is not in the table above. Those report 1, not the 6 this section describes, until that is fixed. It is not whole groups:instance instructions, for example, reaches the classifier and exits 6 as documented, and every heartbeat-wrapped command (instance create,xmd generate,xmd enhance,schema update,schema dry-run) unwraps inside its handler and exits 6.
Breaking change in 0.0.5: HTTP 403 previously exited 4 (auth); it now exits 3 (permission). Scripts that treated exit 4 as “any auth-layer failure” must check stage or handle exit 3 for permission denials.
New in 1.8.0: the release that goes out with the server release that lets an API key create keys, from which org create key mints. It is a minor release, not a patch, because that is when the command first works. Its code is 1.7.8's; its bundled reference describes that server: a 429 names its cause (another mint by this user is still running, this user's keys created too many keys recently, or the server is tracking as many minting users as it can), and a 429 or the server's own 503 is safe to retry after a short wait.
New in 1.7.8: org create key reads the answers of the server release that lets a key create keys. Its own 503 (busy) now says no key was created and the command is safe to run again, where a bare 503 from a proxy still says a key may exist; a 429 (a temporary mint limit, named by the server's message) and a 400 (such as a --name over 255 characters) say no key was created. A 403 is read as "this server does not let a key create keys yet" only when it says nothing but the generic Insufficient permissions; any other 403 is the server's refusal of this key's mint, whatever its wording, so the server may reword that refusal without a CLI release. A 422 is blamed on a server that predates the command only when it names api_role_name.
New in 1.7.7: org key [name-or-prefix] shows one key's role, its effective permission codes (the role plus a super-admin widening) and the clusters it is bound to, read from GET /api-keys; with no argument, the key in use, which the server marks with is_caller (a server that predates the mark is matched by the stored prefix, and two keys that share it ask for a name). A field the server does not give, or clusters this credential cannot all name, are reported unavailable, never as an empty grant or a shorter list, and a selector matches only as a prefix of the stored prefix. org create key --name --role --cluster --out mints a key for this user bound to exactly one cluster the key in use can already see, with a role no wider than its own; the key is written only to the new 0600 --out file and output carries its prefix and path, never the key. It needs a server that lets an API key create keys, which follows this release: until then the server answers 403 before minting anything, and the CLI says the server does not let a key create keys yet. Help and usage errors no longer show internal parser names such as org_create_target.
New in 1.7.6: auth login --auto-approve reads a stored callback only together with its capture signal (under the listener's capture lock), so a callback that landed in time can no longer be seen before its timestamp and mistaken for none; a fix to 1.7.5's deadline handling, with no other change.
New in 1.7.5: auth login --auto-approve no longer cuts a browser callback off at the deadline: a callback captured in time (the listener publishes the capture the moment it lands) is redeemed within the redeem's own bound (two sends of the code, each at the redeem timeout, plus a second), since on the zero-click path the redeem is what makes the key exist; a redeem that outlives that bound ends with the ambiguity stated (a key may exist; deactivate it under API → API Keys) as exit 2, not the timeout's exit 5, since a retry loop on 5 would mint a key per retry; a callback that arrives after Ctrl+C or after a pasted key won is not redeemed at all, a pasted key is not used while a redeem is in flight, and Ctrl+C during a redeem says a key may exist. The login without the flag keeps its deadline exactly as before. The 409 for a repeat redeem names the key's prefix beside its name, since two same-second logins from one host are named alike. The --auto-approve prompt says a first-time address goes through onboarding and must run the command again.
New in 1.7.4: auth login --auto-approve is the zero-click browser handoff for a scripted onboarding: the CLI opens the usual /xmemcli/<challenge> page with ?auto_approve=1&host=<hostname>, and once the browser holds a Console session — an existing one, or one created right then through the Console's own email, Google, GitHub or OIDC sign-in, after which ?next= returns to the same URL (an address with no account yet lands on the Welcome page instead and must re-run the login once onboarded) — the Console obtains a code carrying an intent to mint a key named CLI auto-approved login (<hostname>, <timestamp>) (the email path's shape, with the method named) and navigates the tab to the loopback callback itself; nothing on that surface is clickable, and the delivery works on Safari as well as Chrome and Firefox because it is a top-level navigation, not a fetch. The listener, the state check, the redeem with the verifier and the rc write are the ones every browser login uses; the payload carries method: pkce and auto_approve: true. The key is created only when the CLI redeems the code with its verifier (POST /cli/token), never before, and exactly once per login: a second redeem of the same code is answered 409 naming the key (exit 2 in the CLI, with that message), since a stored key's plaintext cannot be served again — find it under API → API Keys, deactivate it if it is still active, and run the login again. A redeem whose reply is lost after the request was sent is retried once with the same code, which yields the key or that 409; lost twice, the CLI stops with the ambiguity stated (a key may exist; deactivate it under API → API Keys) rather than waiting out its timeout. A failed or abandoned handoff leaves no key behind. The flag is refused beside --email (exit 2). Needs a Console that knows the parameter; an older one runs the manual page for the same URL, which still finishes with a click. The loopback listener's done page is in the Console's style; it still says "Code received" and names the terminal for the result, since it is served before the redeem.
New in 1.7.3: changes.relationship_outcomes reports proposed relationships that are absent when the write completes: replaced when the stored endpoints differ from the proposal, or rejected when no row for the proposal remains (also a restated link the write removed). unavailable means the write already committed in an earlier attempt and its relationship report is unavailable; the write succeeded and no mutations were repeated. Each of these prints as a note: relationship_outcomes … line after the changes, naming the relationship and its endpoints; surviving links stay under created.relations. One entry is different: an unavailable entry with an empty name and no endpoints means the whole changes summary of that earlier attempt is unavailable, object changes and keyless handles included, so empty change blocks do not mean nothing changed. It prints as note: write report unavailable: the write committed; its complete changes summary is unavailable; no mutations were repeated. --json preserves the server's report verbatim, and older servers that omit the bucket continue to work.
New in 1.7.2: a trace ls --search --cursor … answered without the paging fields exits 3 with stage: "paging_unsupported", where 1.7.1 reported stage: "request" and advised retrying the same cursor; the advice now covers a Console that no longer pages too (retry after a short wait, and if it persists restart the walk without --cursor). A plain trace ls --cursor with more than two parts is a usage error (exit 2) saying a three-part cursor belongs to --search, where 1.7.1 sent everything after the first colon as the trace id. A cursor time past 2299-12-31, the Console's own bound, is a usage error too, where the Console answered a bare 400 (or a plain listing served its first page again). trace … wait up to 70 seconds between reads of a Console answer, where they gave up at 30 — enough for one Console query's read queue and deadline; a search that runs several queries in a row can still take longer. A scoped write also reports the stored scoped records no action of it touched under changes.untouched_scope_records — usually text that did not name them, such as "delete this record", or only restated their stored values on a write the diff engine ran, which used to return an empty changes that read as success. In a terminal each one prints as a note: line, next to the other advisory records — note: untouched_scope_records Task task_id='T-1' — where 1.7.1 printed it among the change lines. --json output is unchanged: the block was already kept verbatim. A server that predates the bucket never sends it, so this works against any server.
New in 1.6.1: a removal the server could not tie to exactly one stored record is reported under changes.unmatched_deletes; nothing was deleted for it. In a terminal each one prints as a note: line, next to the other advisory records — note: unmatched_deletes Task task_id='T-999' — where 1.6.0 printed it among the change lines. --json output is unchanged: the block was already kept verbatim. A server that predates the bucket never sends it, so this works against any server.
New in 1.6.0: trace calls lists the LLM calls of one session, a page at a time, and trace call opens one call whole — for super admins, as the Console decides. Both need a Console that serves them; an older one answers 401, exit 4 (auth), for a key that is fine.
New in 1.5.2: a DEEP write can leave a record out when the model's reply for it did not match the schema or ran past the output limit; the server reports each such record under changes.skipped_candidates, and it was not stored. In a terminal each one now prints as a note: line, next to overwritten_field_values and merged_field_conflicts — note: skipped_candidates Dog nickname='Bolt' error_code='model_output_unusable' reason='…' — where 1.5.1 printed it among the change lines. --json output is unchanged: the block was already kept verbatim. A server that skips nothing sends no such bucket, so this works against any server.
New in 1.5.1: write --scope-mode drop asks for a scoped write that skips and reports changes outside its scope instead of failing, and that creates only the records its --scope names — which may not be stored yet. The report is changes.skipped_out_of_scope: one terminal line per operation, type and set of fields, carrying count=N, the number of records it stands for, and naming a record's key only when the --scope named that record. A drop-mode write that skipped everything still returns a changes block, holding that report alone. A server that predates drop mode refuses mode in the scope (exit 3), which is a clean failure; a deployment part-way through rolling it out is not, so publish 1.5.1 only after the server side is fully deployed — see Releasing xmemcli. --scope-mode reject is never sent, so plain scoped writes work against any server.
New in 1.5.1: write and write-status keep the server's changes block — what the write created, updated (field by field, old → new) and deleted, plus bulk summaries and advisory records — verbatim in --json output. In a terminal each change is one indented line: a bulk delete or update reads deleted 3 × Ticket where status='open', one the server refused reads not deleted Ticket: refused — <reason>, the advisory overwritten_field_values / merged_field_conflicts records follow as note: lines, and past 50 lines the rest is counted in one closing line (--json is never truncated); write-status with several ids prints a status line per write, each followed by its changes. changes is omitted when the write changed nothing, so that output keeps its earlier shape; a drop-mode write that only skipped is the one write that changed nothing and still carries the block. write also takes structured mutations (--mutations-file, --mutations-stdin, --delete TYPE:ID) in place of text; the text positional is now optional, and a write with neither text nor mutations, or whose text is empty or only whitespace, is a usage error (exit 2, stage: "usage"). Before 1.5.1 write "" reached the server, whose 400 exited 3 with stage: "request", and whitespace-only text was sent and accepted. A structured write's output carries no extracted, since it runs no extraction; on a text write the tags now read Type(identifier) (Person(name='Ada')), as documented, where they read ?(Type). A malformed --scope (on write and read) or --delete — now including a key field given twice or an empty value — reports stage: "usage", still exit 2; --scope reported "request". --mutations-stdin and --schema-stdin refuse a terminal instead of waiting on it, and every input file and piped input is read by one reader and decoded as strict UTF-8, so an input that is not UTF-8 (--mutations-file, --schema-file, --migration-plan, schema suggestions decide --file, the xmd validate / convert / enhance schema file, or the same bytes piped to --mutations-stdin / --schema-stdin) is a usage error at exit 2 instead of a traceback at exit 1 — or, piped, a garbled write at exit 0 — and a leading UTF-8 byte-order mark is accepted. Wherever an HTTP error from the API is reported as HTTP <status>: …, a body in the API's error envelope now gives the server's own message (HTTP 400: <message>, plus the request field when the server names one) instead of the first 200 characters of the raw body.
New in 1.3.0: exit 8 with stage: "processing" for a write whose server-side wait window expired while the write kept running. In --json mode that document also carries a write_id field (omitted when the server sent no handle), so a script polls with it directly instead of parsing the message. Additive — no previously documented mapping changed — but a script that reads “non-zero, and not a code I recognise” as failed-and-retryable will now retry a write that has not failed, starting a second one the account pays for. Branch on 8 (or on stage) and poll xmemcli write-status <write_id> until it settles.
New in 1.2.0: instance templates lists the ready-made instance shapes the service ships, with the prose to choose between them, and instance create --template <id> builds one from a pinned schema the server already holds. No schema is generated on that path: no description to compose, no xmd generate hop, and the instance comes out identical to the one the console would have made from the same template. (Creating an instance still generates its agent brief afterwards, on this path as on any other.)
New in 1.1.0: auth login records the deployment's own MCP origin in .xmemrc.json as mcp_url (omitted where the server reports none), and mcp both connects there by default and accepts it as the pair its key may reach. Requires 0.0.12 or newer to read such a file — see the note below.
Compatibility change in 0.0.12: an .xmemrc.json carrying a key this release does not recognise is now accepted, and the unknown key ignored; email, api_url, and api_key are still required and still have to be strings. Until 0.0.12 the key set was closed, which made adding a field to the file a breaking change for every command rather than for the one that would read it — a CLI that cannot load the rc cannot resolve a credential for anything. Nothing writes an extra key yet; this release exists so that a later one can.
Compatibility change in 0.0.13 (single-origin deployments): an API base URL's path is now preserved, never stripped — --api-url https://host/xmem builds requests under /xmem instead of reducing to the bare origin. Where the base's path is exactly /xmem, the CLI infers its single-origin siblings on the same host: auth login finds the Console at /console without --console-url, and xmemcli mcp reaches /mcp without --mcp-url (explicit --console-url / --mcp-url and $XMEM_CONSOLE_URL / $XMEM_MCP_URL still win when inference does not apply; on a call that names --api-url …/xmem, sibling inference beats $XMEM_CONSOLE_URL; the MCP origin guard accepts the /xmem ↔ /mcp pair as one deployment). Bare origins and every other path shape behave exactly as before. See cli/.
Two consequences worth knowing. Connect instructions from the API assume 1.0.0 or newer everywhere, and 1.1.1 on a single-origin deployment — earlier releases let $XMEM_CONSOLE_URL steer sign-in and token redemption to a foreign Console. On a single-origin deployment they render auth login --api-url https://host/xmem with no --console-url. The inference is keyed on the conventional mounts (/xmem, /console, /mcp). A deployment that mounts its services under other prefixes is not inferable: name --console-url and --mcp-url explicitly there, which is what its own rendered commands do.
Console instance URLs (1.0.0+): xmemcli auth login https://host/console/instance/<uuid> infers the API base (/xmem) and Console (/console) from that page URL on a single-origin host — no extra flags or env vars. The Connect tab paste prompt uses this form. When no .xmemrc.json exists yet, the CLI stages the inferred api_url into a placeholder rc as soon as login starts; an existing credential file is never rewritten mid-login. Remote plain HTTP is refused (HTTPS or loopback only) — the same rule as the plain URLs below.
Plain single-origin login URLs (1.1.1+): xmemcli auth login https://host/console or …/xmem (trailing slash optional) infer the same sibling pair with no instance id — useful when signing in before you have an instance page open. Remote plain HTTP is refused (HTTPS or loopback only). An existing .xmemrc.json credential is never rebound mid-login; only a missing rc gets a placeholder api_url.
Compatibility change in 1.0.0: console instance page URLs for login (above), immediate api_url staging in .xmemrc.json, and 1.0.0 as the minimum version named by connect setup instructions. Revised in 1.1.1: staging writes only a placeholder when no rc exists (an existing credential file is left alone until login succeeds); single-origin connect instructions name 1.1.1 as their minimum — earlier releases let $XMEM_CONSOLE_URL steer the sign-in Console; and HTTPS-or-loopback now applies to every single-origin login URL, including instance pages, not only the new /console and /xmem forms. A mistaken --api-url http://host/xmem is refused the same way.
Compatibility change in 1.7.1: a bare auth login (no --api-url, $XMEM_API_URL or positional URL) now signs in to the API origin recorded in the nearest .xmemrc.json — found by walking up from --rc-dir, $XMEM_RC_DIR or the working directory, ending at ~/.xmemrc.json. 1.7.0 ignored that file: it signed in to production and wrote the new, production-bound key into an rc in the working directory or --rc-dir. auth login --email already followed the rc, but refused a stg or pp origin as having no known Console. A home rc bound to stg, pp or a local stack therefore makes a fresh project's login mint a key there; pass --api-url https://api.xmemory.ai to sign in to production instead. An rc origin with no known Console (one that is not production, stg, pp, a /xmem base or a local :8000), or one that is not a usable http(s) URL, is now refused (exit 2, naming the file) where it used to sign in to production. Both login paths print the rc-chosen origin and the file before anything is sent (not for the production default). The Consoles of https://api.stg.xmemory.ai and https://api.pp.xmemory.ai are inferred for auth login and trace. Their MCP origins, and dk's (https://dk-mcp.xmemory.ai), are inferred for mcp when no MCP origin is named or recorded in the rc — including for a key named with --api-key and --api-url, which 1.7.0 sent to the production MCP. The pairing check is stricter everywhere it runs: a stg or pp Console with any API but its own origin, or the reverse, is refused whatever path, query or userinfo either half carries, unless the two are a single-origin /console beside its own /xmem; so is a percent sign, backslash or non-ASCII character in either half's host or userinfo. auth login, trace and auth status exit 2 on it; the org permission probe declines to send the key and reports the original 403. When the API comes from the rc: an origin that is neither https nor loopback (localhost, 127.0.0.1, [::1]) is refused (naming a bare origin with --api-url beside an https --console-url accepts it), and if that API names its own Console (a /xmem base its /console, a local :8000 its :8002, stg / pp their table Console), a named Console must be that one, in any spelling of that origin (case, a default port, trailing dots on a named host, localhost / 127.0.0.1 / [::1] for a loopback one) but on the same mount — any other is refused (exit 2), so a $XMEM_CONSOLE_URL exported for one deployment cannot mint a key into the rc of a deployment whose Console is known. Naming the API on the call makes the pair the caller's: --api-url with the Console in --console-url, or $XMEM_API_URL with it in --console-url or $XMEM_CONSOLE_URL. auth status, trace and the org permission probe hold a named Console to the same rule while the call names no API: the first two exit 2, saying how to keep that Console, and the probe declines to send the key and reports the original 403. There, naming the API on the call (--api-url or $XMEM_API_URL, which must match the rc's origin the key is bound to) lifts the rule, and the Console still comes from --console-url (trace) or $XMEM_CONSOLE_URL — unlike login, --api-url does not turn $XMEM_CONSOLE_URL off for these. Explicit origins are held to the same shape: an --api-url / $XMEM_API_URL, or the API of a positional single-origin URL, with userinfo, a query, a fragment, a non-http(s) scheme, a percent-encoded or non-ASCII host (spell an internationalised host as xn--…), or a host that is neither dot-separated labels of letters, digits, - and _ nor a bracketed IP address, is refused (exit 2) even when no Console is named, where 1.7.0 recorded it. A recorded api_url keeps an IPv6 literal's brackets, and the host as it was written (a trailing dot is recorded, and compared as the same host); 1.7.0 and 1.7.1 read each other's files. auth status refuses an api_url it cannot parse (exit 2, naming the rc it came from) where 1.7.0 crashed, exited 3 or, for one such as http://::1:8000, went on to use it and exited 0. auth login refuses (exit 2), before it writes or mints anything, an rc directory (--rc-dir, $XMEM_RC_DIR or the working directory) that is unwritable or unreadable; one whose nearest existing parent is a file, a broken symlink, a symlink loop or unwritable; and a working directory that no longer exists when the rc directory is relative to it. 1.7.0 minted the key and then could not save it (or, on Python 3.12, crashed on a loop). A login that saves nothing, answered by a matching --api-key or rc, is not refused. A leading ~ in --rc-dir, $XMEM_RC_DIR, --binding-dir or $XMEM_BINDING_DIR is now the home directory for every command, where 1.7.0 read and wrote a directory literally named ~ when the shell left it unexpanded (--rc-dir=~/x). If such a directory exists (./~/x), it is still the one used, so a credential or binding 1.7.0 wrote there keeps being read, and auth logout removes that one; move its files to the home path and delete it to switch. The browser login now moves a malformed rc it replaces aside to .xmemrc.json.invalid (mode 0600), as the email login already did, where 1.7.0 overwrote it. Both paths warn about the malformed file before signing in, and refuse (exit 2) before minting when every backup name beside it is taken; if the file still cannot be moved after the mint, the login exits 3, naming the new key's prefix, and overwrites nothing. On 1.7.0 and older, signing in to pp or stg needs --api-url and --console-url together: a browser login from an rc bound to pp with --console-url alone is refused (--email accepted it), and with no flags the login goes to production.
See also ACCOUNTS_AUTH.md for the server-side 401/403/404 rules.
Help
xmemcli supports root -h / --help (same overview as bare xmemcli) and the help subcommand for nested topics.
| Invocation | What you get |
|---|---|
xmemcli |
Full command overview (grouped list of every capability) |
xmemcli help |
Same as bare xmemcli |
xmemcli help options |
Global flags (--api-url, --api-key, --json, …) |
xmemcli help <topic> |
Usage, options, and subcommands for that topic |
xmemcli <cmd> … -h / --help |
Same as help <topic> for that command path |
Unknown help topics exit 2 (same as other usage errors).
Every command in this document has help. Examples:
xmemcli help write
xmemcli help write-status
xmemcli help read
xmemcli help org
xmemcli help org list instances
xmemcli help instance create
xmemcli help schema
xmemcli help schema get
xmemcli help schema update
xmemcli help schema dry-run
xmemcli help schema migrations
xmemcli help schema migrations list
xmemcli help schema migrations get
xmemcli help schema suggestions
xmemcli help schema suggestions review
xmemcli help schema suggestions decide
xmemcli help schema suggestions apply
xmemcli help xmd
xmemcli help xmd generate
xmemcli help xmd enhance
xmemcli help xmd validate
xmemcli help xmd validate-yaml
xmemcli help xmd validate-json
xmemcli help xmd convert
xmemcli help trace
xmemcli help trace ls
xmemcli help trace get
xmemcli help auth login
xmemcli help quota
xmemcli help options
Nested topics work at any level that exists in the parser (help org, help org list, help org list keys, …). Unknown topics print a short error and suggest xmemcli or help options.
What xmemcli does not do
| Area | Use the Console instead |
|---|---|
| Quota increases | No quota request-increase. Observe with xmemcli quota; raise limits in Billing / Quotas UX. |
| Routine API key creation | Post-onboarding: API Keys UI (CLI opens that flow via /xmemcli). |
| Billing & plans | Console only |
| Users, roles, org admin | Console only |
| Instance chat | Console only (trace inspection is xmemcli trace …, see Trace) |
| Cluster create/delete | CLI lists clusters; provisioning in Console |
read --extraction deep |
Server has no read-depth knob today |
| Raw REST proxy | Curated response fields only |
| Instance deletion | Human operators only — a hidden instance delete exists for interactive TTY use (type yes to confirm). It is omitted from help and must not be used by agents or automation. Console UI remains the primary human path. |
On HTTP 402 (quota exhausted), stop and ask a human to extend quota in the Console.
Global flags & environment
These apply before any subcommand (xmemcli help options).
| Flag | Env var | Purpose |
|---|---|---|
--api-url |
XMEM_API_URL |
API origin (default https://api.xmemory.ai) |
--api-key |
XMEM_API_KEY |
Bearer API key |
--instance-id |
XMEM_INSTANCE_ID |
Default instance for read/write and cluster derivation |
| --rc-dir | XMEM_RC_DIR | Where auth login writes .xmemrc.json; reads walk up toward $HOME |
| --binding-dir | XMEM_BINDING_DIR | Where binding commands look for .xmemory.json; reads walk up toward $HOME and merge every scope |
| --console-url (accepted by trace … and auth login; $XMEM_CONSOLE_URL is read by auth status too) | XMEM_CONSOLE_URL | Console origin serving the trace views (inferred for the public, stg, pp and local API pairs and the /console sibling of a /xmem base; required for any other API origin). A named Console that provably does not pair with the API origin is refused; the refusal names the setting that supplied it, since auth status does not accept the flag |
| --json | — | Force one JSON document on stdout |
| --verbose | — | Add trace_id / console_url when present (never SQL, diff plans, or internals) |
Credential resolution: --api-key → $XMEM_API_KEY → nearest .xmemrc.json → Not logged in — run xmemcli auth login first.
.xmemrc.json shape: {email, api_url, api_key}, all three required and all three strings, plus an optional mcp_url recorded by auth login. Keys beyond those are ignored rather than rejected (see the 0.0.12 note above), so a file written by a newer CLI still loads here.
context is the one exception, and it is a security boundary. Every other command walks up
from the current directory for the nearest .xmemrc.json, which is deliberate: a person chose
that directory and ran the command in it. context has neither — a session-start hook runs it
unattended, in whatever tree the editor happened to open — so it resolves the credential from
$HOME only, and consults a project .xmemrc.json only when the caller named that source
explicitly with --api-key / $XMEM_API_KEY or --rc-dir / $XMEM_RC_DIR. Without the pin, a
cloned repository could ship a key and an origin and have both used automatically. This is a
rule rather than a detector: earlier versions tried to detect a checkout-supplied credential
and each delivery mechanism turned out to be a fresh bypass.
Origin resolution: --api-url → $XMEM_API_URL → rc api_url → default — with one escape hatch: when the key comes from --api-key / $XMEM_API_KEY (not from the rc), the rc's api_url is not consulted and the origin falls back to the built-in default (https://api.xmemory.ai) unless you also set --api-url / $XMEM_API_URL. That keeps an explicitly supplied key from being silently paired with an unrelated origin in a project .xmemrc.json. If $XMEM_API_KEY is set without $XMEM_API_URL, the CLI warns once per invocation.
MCP origin resolution (mcp only): --mcp-url → $XMEM_MCP_URL → the rc's mcp_url → the API base's /mcp sibling (single-origin) or its hosted pair (stg, pp, dk) → default (https://mcp.xmemory.ai). The rc rung follows the same escape hatch as the API origin: a key named with --api-key / $XMEM_API_KEY never inherits an origin from a project file.
Request identification (new in 1.3.0): every outbound request carries X-Xmemory-Client: xmemcli/<version> (python <version>; <system>-<machine>), e.g. xmemcli/1.3.0 (python 3.12.4; Linux-x86_64). Each field is reduced to letters, digits, ., _ and -, so nothing an OS or a patched interpreter reports can forge the note's own punctuation or fail the request when it is sent; a field with nothing usable left reads unknown. No hostname is included. The server uses this header to attribute traffic to a client. The CLI sets no User-Agent of its own, then or now: the installed urllib opener supplies its default, so the User-Agent the server sees is Python-urllib/<version> and the identity comes from the header above. Direct API requests from 1.2.0 and earlier send neither, so they record client_name: python-urllib -- indistinguishable from any third-party Python caller. Reading a drop in that bucket as third-party traffic leaving is therefore wrong; it is old CLIs upgrading. Three outcomes are distinct and must not be read as one figure: a recognised header, the other bucket a present but unrecognised header lands in, and an absent property, which means neither header named a client. Before 1.3.0 the email sign-in exchange was the only path that named itself, and it sent a bare xmemcli/<version> with no platform hint; it now sends the same header and the same value as every other path. What the server records for it still differs, though, and not because of the CLI: the console-facing calls (email sign-in, token redemption, whoami) reach the accounts API through the console, which rebuilds the request on its own HTTP client and forwards only Cookie, Content-Type, Authorization and Host. X-Xmemory-Client does not survive that hop, so those land as console. The attribution described above is what direct API calls record.
Instance resolution (read/write): --instance-id → $XMEM_INSTANCE_ID → if exactly one instance is visible, auto-select with a stderr warning → else error.
Output: Pipes and non-TTY stdout → JSON. Interactive TTY → one-line summaries unless --json.
Metadata
Release files for xmemcli 1.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| xmemcli-1.8.0.tar.gz | 364.5 kB | Without provenance | Details for xmemcli-1.8.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| xmemcli-1.8.0-py3-none-any.whl | Python 3 | none | any | Details for xmemcli-1.8.0-py3-none-any.whl |
Total release size: 684.3 kB
Release files / xmemcli-1.8.0.tar.gz
| Download URL | xmemcli-1.8.0.tar.gz |
|---|---|
| Size | 364.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a78aee4aa93899a61f9dc22a7fb4cf60a9fc2a6e7607cf1bbafc7a31ca664653
|
|
BLAKE2b-256 checksum How to use checksums |
3a978fa88b6c146cb3f8a8bea0353104c857d29e957b2cda5e5b9d538476452c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / xmemcli-1.8.0-py3-none-any.whl
| Download URL | xmemcli-1.8.0-py3-none-any.whl |
|---|---|
| Size | 319.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8da93584511142578898991ab3a3a472a52bdaa9cde9723eed53f440e16c40a4
|
|
BLAKE2b-256 checksum How to use checksums |
928c246c17b04378d417e3c32cb97c48feb82f2b010ba81388a7f8590e61f9b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.6 {"installer":{"name":"uv","version":"0.13.6","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for xmemcli 1.8.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.