Skip to main content

polign-recall

A Python client for Recall, memory and state for agents. Requires Python 3.10+.

pip install polign-recall

That is the whole install. pip also brings the polign_db package, which holds the polign CLI and polign-server binaries for Linux, macOS and Windows, so there is nothing else to download.

The client has two halves, matching Recall's two contracts. Memory is what the agent knows: remember, ask, forget_text and the typed calls, the Memory API. State is where the agent is: resume and the ResumedAgent it returns, the State API.

Memory

from polign_recall import Client

with Client(local_dir="./recall-data", extract_model="anthropic:claude-haiku-4-5-20251001") as memory:
    memory.remember(text="I switched from helix to zed last week.")
    for m in memory.ask("Which editor do I use?"):
        print(m.text, m.since, [e.text for e in m.before])  # user prefers editor: zed ... ['helix']
    memory.forget_text("my editor")

remember(text=...) hands the server a passage; the model named by extract_model works out the facts in it, and a newer fact replaces an older one. It returns a TextResult listing what was filed and what each statement replaced. ask returns Memory sentences, each with since, days_ago, and what it replaced under before; it accepts as_of. forget_text withdraws the facts a description names and returns them; the texts they came from stay as the record. Without extract_model, remembered text is kept as written: ask finds it by its words, but it replaces nothing, and forget_text needs a model.

Nothing is deleted, so the record of corrections can be read back:

for t in memory.history_text("my editor"):       # every statement, oldest first
    for step in t.changes:
        print(step.when, step.change, step.ended, step.began)
memory.ask("Which editor do I use?", as_of="2026-10-01T00:00:00Z")  # believed then
memory.diff(since="2026-10-01T00:00:00Z")           # what ended and began since

history_text returns a Timeline per thing the question reaches, including things since forgotten: now is what is believed, and each Step says whether it stated, replaced or withdrawn something, with the sentences it ended and began. diff(since, until=None) returns a Change per thing whose beliefs differ between the two instants. Both need a recall server newer than 0.21; an older one raises RecallError with code unsupported.

local_dir keeps the database on this machine. The first client to open the directory starts a polign-server for it in the background, listening on localhost only and protected by a key stored in the directory. Later clients, including ones in other processes, share that server. It keeps running after your program exits; its process id is in runtime.json and its log in server.log, both inside the directory. Managed local databases work on Linux and macOS.

backend, backend_url and backend_key name any database, the same three names as recall -backend, -url and -key: backend is "local", "polign", "pgvector", "mongodb" or "qdrant", the URL is in that backend's own form, and the key is the credential when the URL does not carry one. local_dir=X is the short spelling of backend="local", backend_url=X.

Client(backend="polign", backend_url="http://memory.internal:23000", backend_key="plgn_...")
Client(backend="pgvector", backend_url="postgres://recall:pw@db.internal/recall?schema=memory")
Client(backend="qdrant", backend_url="https://x.cloud.qdrant.io:6333", backend_key="...")

Given any of the three, the client hands the binary exactly those and nothing the environment says about a database. Given none, the recall binary resolves it: RECALL_BACKEND, RECALL_BACKEND_URL and RECALL_BACKEND_KEY in the environment, then what recall setup saved, then a local database in ~/.local/share/recall that it runs itself and that every agent on the machine shares. So a bare Client() works on a fresh machine with nothing configured. The names used before recall 0.23 (POLIGN_URL and the rest) still work in the environment, and a client given backend= against an older binary says the same thing in the names that binary knows. Client.database says where memory ended up, as the binary resolved it: a Database with the backend, the url (a directory for local) and, for local, the loopback server address; None from a binary older than 0.23 or a recall serve.

The client owns a long-lived recall mcp -write -text subprocess and shares the Go implementation's validation and fold. Use write=False for a read-only connection. It runs the recall binary that this package's platform wheel installs next to python; on a platform without one it runs recall from PATH, and without recall it falls back to polign mcp -memory-only from polign_db 0.13 or earlier. command=[...] overrides all of these.

The model is provider:model: anthropic:<model>, openai:<model>, or ollama:<model>, with keys from ANTHROPIC_API_KEY or OPENAI_API_KEY. POLIGN_EXTRACT_MODEL in the environment does the same.

Typed memory

With typed=True, the client uses the typed tools (recall mcp -typed, recall 0.18 or later): your code names the subject, predicate and value, over a fixed vocabulary.

with Client(local_dir="./recall-data", typed=True) as memory:
    memory.remember("user", "prefers_editor", "vim")
    changed = memory.remember("user", "prefers_editor", "neovim")
    current = memory.recall("user", "prefers_editor")[0]
    print(current.value, current.replaced[0].value)  # neovim vim
    print(memory.history("user", "prefers_editor"))  # both statements
    for step in memory.timeline("user", "prefers_editor").changes:
        print(step.when, step.change, step.ended, step.began)  # ... replaced vim -> neovim
    memory.forget("user", "prefers_editor", "neovim")

history returns the raw events; timeline tells the same record as changes, in the same Timeline and Step types history_text returns, with subject and predicate set. diff(since, until=None, subject=None) works here too, and each Change also carries its subject, predicate, and the beliefs before and after.

Read predicates() for the vocabulary: the starter registry, or the file named by POLIGN_PREDICATES. remember(text=..., statements=[...]) accepts proposals from your agent's model; every statement must have subject, predicate, typed value, and evidence quoting the text exactly. A proposal that names an unlisted predicate is dropped, and the whole text is kept as a note either way. With extract_model and no statements, the server's model proposes them over the same vocabulary.

The text calls (ask, forget_text, remember(text=...) alone) raise ValueError on a typed client, and the typed calls (recall, forget, history, predicates) raise on a text client. With command=[...] or url=..., the client follows whichever tools the server lists; typed=True or text=True against the other surface is an error at open.

recall(..., as_of=...) accepts an RFC3339 string or timezone-aware datetime. forget requires a typed value or explicit all=True; false and zero remain values. Forgetting retracts a belief and retains its historical events.

Errors raise RecallError with a code and, for a failed extraction batch, any reported partial results. Calls are serialized, timeout after 120 seconds by default, and never automatically retry writes. A timeout closes the transport; inspect history using a new client before retrying an uncertain write.

Connecting to a server

When memory is served by recall serve rather than a local process, give the client the server and one credential and it speaks HTTP instead:

from polign_recall import Client

client = Client(url="http://recall.recall.svc:8080", api_key="rcl_...")

Inside a Kubernetes sandbox the credential is the pod's projected service account token, which the server exchanges for a short-lived key and the client renews:

client = Client(url="http://recall.recall.svc:8080", token_file="/var/run/secrets/recall/token")

Client.from_env() reads RECALL_URL, RECALL_API_KEY and RECALL_TOKEN_FILE (default /var/run/secrets/recall/token when it exists) and falls back to a local process when RECALL_URL is unset, so the same program runs on a laptop and in a sandbox. Over HTTP the server decides whether it serves the text or the typed tools and whether the resume tools exist; the client finds out when it connects.

State

Memory is what the agent knows. State is where the agent is: one set of records per agent id, holding its working state, its turns, large tool outputs, pointers to its work, and the tool calls it began. A lease on the id keeps one process acting for the agent at a time. The contract is docs/state-api-v1.md; it is a beta surface, so the calls here may change in a minor release with a note in the changelog, while the records they write are stable.

Resuming an agent

An agent that crashes or moves to another machine can pick up from its own records instead of a snapshot of its process. Open the client with agent=True and call resume:

from polign_recall import Client

with Client(local_dir="./recall-data", agent=True) as client:
    with client.resume("billing-migrator") as agent:
        print(agent.context.briefing)  # hand this to the model as its starting context
        agent.update_working_state(goal="Move billing to the v2 API",
                                   plan=["find call sites", "migrate them", "run the tests"])
        agent.record_turn("user", "Start with the charge endpoint.")
        agent.set_pointer("wip", "git_ref", {"repo": "github.com/acme/billing", "branch": "agent/wip"})
        agent.milestone("call sites found", progress="12 call sites listed")

The first resume of an id starts the agent fresh (context.fresh is true). Every later one rebuilds context from what the agent wrote: its working state, pointers to its work, relevant memories, and its most recent turns, trimmed to token_budget. context.briefing is all of that as one text for the model; the same parts are also there as fields.

resume takes a lease on the agent id, so only one process acts for it at a time. While another process holds it, resume raises RecallError with code "lease_held". The lease is renewed in the background and handed over when you call release(), leave the with block, or close the client.

If the process before crashed without releasing, resume has to wait for its lease to expire. When you cannot wait, as on a live call, pass defer_lease=True: resume returns the context at once without the lease, because reading cannot conflict with anyone. Writes then raise RecallError with code "lease_not_held", so keep them in a buffer and call agent.acquire() until it returns True:

agent = client.resume("call-42", defer_lease=True, lease_ttl=6)
greet_with(agent.context.briefing)  # no waiting
while not agent.acquire():          # False while the crashed process's lease is live
    time.sleep(1)
agent.record_turn("assistant", "Sorry, we got cut off.")

Once it holds the lease, anything the crashed process wrote after the resume is picked up, and new turns continue after it.

The other methods write what the next resume reads: update_working_state (fields you leave out are kept), milestone, record_turn (a turn longer than the output threshold is stored whole and the turn keeps a reference), store_output and fetch_output for large tool results, set_pointer, remove_pointer and pointers, and recent_turns and working_state_history to read back.

Tool calls that touch the world

The records above say what the agent was doing, not whether its last tool call happened. Record each call that changes something before it runs, and close it when it returns:

action = agent.begin_action("send_email", "external", {"to": to, "subject": subject})
result = mailer.send(to, subject)
agent.end_action(action.seq, "done", result=result)

The class says what running the call again would do: "pure" (reads only), "idempotent" (repeating it with action.key does nothing more, so pass the key on) or "external" (it could happen twice). If the process dies between begin_action and end_action, the call is still open on the next resume. Interrupted pure calls are closed for you and external ones are marked unknown. Every call still open is in context.pending_actions and at the top of the briefing, as one to check before repeating.

agent.reconcile(resolver) settles them. The resolver gets each open action: for an idempotent one it runs the call again with action.key; for an external one it asks the outside system whether it happened. It returns ActionEnd("done") or ActionEnd("failed"), or None when it cannot tell. Each settled outcome is written to the agent's history, so the model sees it, and context is rebuilt. Recall never runs a tool itself.

State over HTTP

resume and everything on ResumedAgent work the same against a recall serve, through Client(url=..., api_key=..., agent=True). The server holds the agent, and its lease, between requests; agent.epoch is the lease epoch it issued, and the client sends it as If-Lease on every call so that a client the server no longer holds the agent for is refused with RecallError code "lease_lost" rather than writing over its successor. After a server restart the held agents are gone: calls raise with the message not resumed, and client.resume starts over from the records.

Other languages reach the same operations at POST /v1/agent/<verb> with the tool's arguments as the body and the epoch in If-Lease or an epoch field; see the State API.

Metadata

Release files for polign-recall 0.24.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for polign-recall 0.24.0
File Size Uploaded Provenance Actions
polign_recall-0.24.0.tar.gz 48.4 kB With provenance Details for polign_recall-0.24.0.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for polign-recall 0.24.0
File Actions
polign_recall-0.24.0-py3-none-win_arm64.whl Python 3 none Windows ARM64 Details for polign_recall-0.24.0-py3-none-win_arm64.whl
polign_recall-0.24.0-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details for polign_recall-0.24.0-py3-none-win_amd64.whl
polign_recall-0.24.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.musllinux_1_1_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64, Linux musl 1.1+ x86-64 Details for polign_recall-0.24.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.musllinux_1_1_x86_64.whl
polign_recall-0.24.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.musllinux_1_1_aarch64.whl Python 3 none Linux musl 1.1+ ARM64, Linux glibc 2.17+ ARM64 Details for polign_recall-0.24.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.musllinux_1_1_aarch64.whl
polign_recall-0.24.0-py3-none-macosx_12_0_x86_64.whl Python 3 none macOS 12.0+ x86-64 Details for polign_recall-0.24.0-py3-none-macosx_12_0_x86_64.whl
polign_recall-0.24.0-py3-none-macosx_12_0_arm64.whl Python 3 none macOS 12.0+ ARM64 Details for polign_recall-0.24.0-py3-none-macosx_12_0_arm64.whl
polign_recall-0.24.0-py3-none-any.whl Python 3 none any Details for polign_recall-0.24.0-py3-none-any.whl

Total release size: 58.5 MB

Release files / polign_recall-0.24.0.tar.gz

Download URL polign_recall-0.24.0.tar.gz
Size 48.4 kB
Tags Source
SHA-256 checksum
How to use checksums
9642d86f6de427c01de7bbaf6e4f8361f62ca253c3d0198030ebde4aabfec129
BLAKE2b-256 checksum
How to use checksums
00704970e850532d149ee5191b429f4e99ac2e44c13cc16542369594f46e9aa2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-win_arm64.whl

Download URL polign_recall-0.24.0-py3-none-win_arm64.whl
Size 9.1 MB
Tags Python 3 Windows ARM64
SHA-256 checksum
How to use checksums
1f965cb2b918ec13a001ed5892e63334b76e757b869059f6a2c953146379b742
BLAKE2b-256 checksum
How to use checksums
4cafade8988719b0e7c0893de15291591884a9e42d48e4de0fc7c9eee7fba551
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-win_amd64.whl

Download URL polign_recall-0.24.0-py3-none-win_amd64.whl
Size 10.4 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
84261736745e3d2dd2326d35aad1dfd3efa3ce90b7d3dd482596ab1514db9c11
BLAKE2b-256 checksum
How to use checksums
0963b5a747131cbd6e02d1b9ad74385933a6cf8a6ceb56e2e6bff4b9069b82c8
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.musllinux_1_1_x86_64.whl

Download URL polign_recall-0.24.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.musllinux_1_1_x86_64.whl
Size 10.2 MB
Tags Linux glibc 2.17+ x86-64 Linux musl 1.1+ x86-64 Python 3
SHA-256 checksum
How to use checksums
0b2e6a69df8b29f1329e1c7e44c25f0a5fe2afccbf07625411973c50893b3d33
BLAKE2b-256 checksum
How to use checksums
1a4578f0909d360e4f63d5b4f70040908aa2cdde6e3ddd673242f34b3777d8c6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.musllinux_1_1_aarch64.whl

Download URL polign_recall-0.24.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.musllinux_1_1_aarch64.whl
Size 9.0 MB
Tags Linux glibc 2.17+ ARM64 Linux musl 1.1+ ARM64 Python 3
SHA-256 checksum
How to use checksums
df6e955f4362d8dc5e4aa679995b9949d8113d29207f7569968d7460fefad38e
BLAKE2b-256 checksum
How to use checksums
4b833a964123d0298f0ac339af4280a681b8695c93a0452aa9b069799a75b94d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-macosx_12_0_x86_64.whl

Download URL polign_recall-0.24.0-py3-none-macosx_12_0_x86_64.whl
Size 10.4 MB
Tags Python 3 macOS 12.0+ x86-64
SHA-256 checksum
How to use checksums
f64dce4cce1e94ac95e927aa0bcc39474de4f0e0d9d32b6a7ae1c7372d4f652b
BLAKE2b-256 checksum
How to use checksums
0e782aeae84338fd1e8f8da5c1ed7224ca64aa3709c8ac010a54b56e3a1ae044
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-macosx_12_0_arm64.whl

Download URL polign_recall-0.24.0-py3-none-macosx_12_0_arm64.whl
Size 9.4 MB
Tags Python 3 macOS 12.0+ ARM64
SHA-256 checksum
How to use checksums
c1344dd65d5344d36fa3eed1d48392206cf875c1efbeb5e4831846ad2f0fcd67
BLAKE2b-256 checksum
How to use checksums
03b917e7f3ed414835d3902e3426fea5b43806e808076419470d5df25c03f53a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Release files / polign_recall-0.24.0-py3-none-any.whl

Download URL polign_recall-0.24.0-py3-none-any.whl
Size 32.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
db4e56daf4170b9c2550668f7f22de92771564f46f7e10ad7b1579903fcbe7f9
BLAKE2b-256 checksum
How to use checksums
74734b2c999101309b6dc883746fb00567d6ae733a3da70ea4535c3d523cc064
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

Security for polign-recall 0.24.0

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.

Full provenance

All 8 files in this release have been uploaded with provenance metadata.

Select from 8 files

Attestation for polign_recall-0.24.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 30, 2026.

Transparency log

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page