plugmem

⚠️ Experimental. plugmem is mostly an AI-built experiment — written with the help of a small local model (Qwen3.6-35B-A3B-UD-Q4_K_XL.gguf) and various Claude models, in roughly equal measure. Expect non-professional design choices, rough edges, broken behavior, or mistakes. Use it at your own risk.

An embeddable bitemporal memory database for local-first applications and agents, embedded in your Python process. It stores short facts and answers a query with ranked facts and edges plus an optional bounded rendered block.

File-backed on disk, no server, no daemon. It links into your process the way SQLite does: the engine is plugmem-host compiled to a CPython extension module through PyO3, so the data lives in mapped files rather than in the interpreter's heap. Every call releases the GIL for the duration of the work.

No embedding model is required. Three of the four retrieval sources — text, graph and time — need nothing but the database. An embedder is optional and adds the fourth; see Do you need an embedder? for what changes when you add one and what you give up without it.

Contents: Install · Quick start · Do you need an embedder? · What it stores · Two clocks · How recall works · API · Errors · Configuration · Threads and the GIL · Typing · Many memories · What it is not for

Install

$ pip install plugmem

Prebuilt wheels cover Linux, macOS and Windows on x86-64 and arm64. One wheel per platform serves every CPython from 3.10 on — it is built against the stable ABI, which does not change between versions — plus a separate wheel for the free-threaded 3.14t build, which has an ABI of its own. No toolchain, no build step.

Quick start

import plugmem

db = plugmem.Plugmem.open("agent.plugmem")

db.remember("the user prefers tokio", entity="user", tags=["pref"])
db.remember("the release ships on friday", entity="release")

res = db.recall("tokio", k=5)
print(res.rendered)

db.close()

## memory
- [f0] user: the user prefers tokio (2026-08; active) #pref

Plugmem is also a context manager, which is the usual way to write it:

with plugmem.Plugmem.open("agent.plugmem") as db:
    db.remember("the deploy target is fly.io", entity="release")

open is a static method rather than a constructor because it takes the file's exclusive lock, replays the journal and maps the snapshot — work proportional to what is on disk, and worth naming rather than hiding behind Plugmem(...).

Do you need an embedder?

No, and it is worth being precise about what that costs, because the answer decides how you should write your queries.

Without one, three sources answer: BM25 over the text, the entity graph, and time. That is a working memory with no model, no API key, no network call and no per-query cost. What you lose is matching by meaning: BM25 needs shared words, so the query above finds the fact because both say "tokio". Ask it the way a person would —

db.recall("which runtime?", k=5)   # → no facts: no word in common

— and you get nothing back, because "runtime" appears nowhere in "the user prefers tokio". Anchor on an entity (entities=["user"]) or use the words the fact uses, and it answers.

With one, a fourth source runs: each fact and each query is embedded, and cosine similarity finds the fact whose meaning is close even when no word matches. "which runtime?" then reaches "the user prefers tokio". The cost is a provider round trip per write and per text query, an API key, and a dim that is fixed for the life of the database.

You can also skip the provider and pass vectors yourself — see Bringing your own embedding — which is the route for a local model or one that is not an OpenAI-shaped HTTP endpoint.

Sensible default: start without one. Tag and anchor your facts, see whether lexical recall is enough for your queries, and add an embedder when you catch yourself wishing a query had understood a synonym.

What it stores

A fact is one short statement plus the things that make it findable and datable:

db.remember(
    "the user prefers tokio",
    entity="user",                       # the subject
    tags=["pref", "runtime"],            # filters
    links=[("works_on", "plugmem")],     # typed edges from the subject
    metadata={"src": "chat-2026-08-05"}, # opaque to the engine
    valid_from=1_767_225_600_000,        # when it became true (unix ms)
)

metadata is a string-to-string map the engine never interprets. It is where a URI to the real payload goes, or a mime type, or a key in your own system — the fact stays short and searchable while the bulk stays wherever you keep bulk.

remember returns the new id and any live facts that look like duplicates or contradictions:

out = db.remember("the user prefers async-std", entity="user")
for hint in out.similar:
    print(hint.id, hint.score, hint.reason)   # 0 0.87 LexicalOverlap

The engine never merges on its own. You decide: revise if it changed, forget if it was wrong, or nothing if both are true at once.

Two clocks

This is what separates plugmem from a store that overwrites. Every fact carries two independent intervals:

recorded_at — when this memory learned it. Immutable.
valid_from / valid_to — when the statement was true in the world.

revise closes the old interval instead of deleting the old row:

JAN = 1_767_225_600_000   # 2026-01-01
JUL = 1_782_864_000_000   # 2026-07-01

berlin = db.remember("the user lives in berlin", entity="user", valid_from=JAN)
db.revise(berlin.id, "the user lives in lisbon", entity="user", valid_from=JUL)

db.recall("lives", entities=["user"])
# → [the user lives in lisbon]

db.recall("lives", entities=["user"], closed=True)
# → [the user lives in berlin, the user lives in lisbon]

The Berlin fact is still there, with valid_to now set to JUL — the instant its successor took over. Nothing was overwritten, so "where did the user live in March" remains answerable.

as_of asks the bitemporal question, and it filters on both axes:

db.recall("lives", entities=["user"], as_of=FEBRUARY)
# → []

Empty, and that is the correct answer rather than a bug. Both facts were recorded today, so as of February this memory did not know either of them. A memory that answered would be claiming knowledge it did not have. Ask as of an instant the memory had already reached and you get whatever was true then.

How recall works

Four sources run and are fused with reciprocal-rank fusion, then a recency boost is applied. Tags filter; they are not a source.

Source	What it matches	Needs an embedder
lexical	BM25 over the fact text	no
graph	facts reachable from the anchors in `entities`	no
time	facts inside the `range` window	no
vector	cosine over embeddings	yes

res = db.recall(
    "who owns the deploy",
    tags=["ops"],                  # a filter, not a source
    entities=["release"],          # graph anchors
    range=(FROM_MS, TO_MS),        # window over recorded_at
    k=8,                           # facts to return
    token_budget=512,              # size of `rendered`
    graph_depth=2,                 # hops from the anchors, this call only
)

for fact in res.facts:
    print(fact.id, fact.score, fact.sources)
for edge in res.edges:
    print(edge.src, edge.rel, edge.dst)
print(res.rendered)                # the bounded block
print(res.truncated)               # True if something was left out

res.facts and res.edges are the structured answer; res.rendered is a convenience for callers that want a block of text under a token budget. Neither is more real than the other.

graph_depth is per call because how wide a net to cast belongs to the question: "what is this person's stated preference" wants fewer hops than "what is known around this person". There is no ceiling — the walk is bounded by its own entity and edge caps.

API

Everything is synchronous. See Threads and the GIL for why that is the right shape and not a limitation.

Verb	Does
`Plugmem.open(path=None, *, dim=None, read_only=False, config=None)`	open or create; resolves `PLUGMEM_DB`, then `[database].path`, then the platform data path
`remember(text, *, entity, tags, links, metadata, valid_from, vector)`	store one fact
`remember_many(facts)`	store a batch — one journal write, one embedding round trip
`revise(id, text, ...)`	close a fact's interval and record the successor
`recall(query=None, *, tags, entities, as_of, range, k, closed, token_budget, ef, graph_depth, vector)`	the ranked answer
`forget(id)`	tombstone a fact; `maintain` purges it later
`link(src, rel, dst, *, provenance)` / `unlink(src, rel, dst)`	open or close a typed edge
`get(id)` / `tags_of(id)` / `stats()`	one fact's card, its tags, engine counters
`export()` / `export_page(cursor)` / `export_edges(on_batch)`	dump facts, dump them in pages, stream edges
`verify()` / `scrub(budget=None)`	logical check; byte-level check
`maintain(mode="auto")` / `checkpoint()`	housekeeping; publish a snapshot
`generation()` / `refresh()`	read-only handles: which snapshot, and move to the newest
`config_warnings()` / `path()` / `close()`	config typos, the resolved file, release it

Module level: version(), about(), settings_help(), skill(), skill_full(), skill_version(), recover(src, dst), and the export_pages(db) generator.

Bringing your own embedding

Pass vector and nothing is sent to a provider — it replaces the embedder for that call. This is the route for a local model, or one that is not an OpenAI-shaped HTTP endpoint:

db = plugmem.Plugmem.open("agent.plugmem", dim=384)
db.remember("the user prefers tokio", entity="user", vector=my_model.encode(text))
db.recall(vector=my_model.encode("which runtime?"), k=5)

The length must equal the configured dim, which is fixed when the database is created.

Backing up: facts are only half of it

A fact names its own tags and metadata, but an edge is a statement between two entities and outlives any single fact. A complete dump is both streams:

facts = []
for page in plugmem.export_pages(db):      # bounded pages, not one big list
    facts.extend(page.facts)

edges = []
db.export_edges(edges.extend)              # called with a list at a time

export_edges hands over batches rather than one edge per call, because each call has to reacquire the interpreter; the walk itself runs with the GIL released. It returns the total.

Checking a file has not rotted

verify() asks whether the indexes agree with the facts. scrub() asks whether the bytes on disk are the bytes that were written — it recomputes the stored checksums, which is what catches a flipped bit that the structure happily accepts.

with db.scrub() as scan:
    for progress in scan:
        print(f"{progress.done_bytes}/{progress.total_bytes}")

It is paced by you rather than run to completion, so it is affordable on a live database. Holding the object holds a lock on the snapshot generation it is scanning, so the writer cannot recycle that file underneath it — finish the scan or close it, which the with block does for you.

Repairing a damaged file

report = plugmem.recover("damaged.plugmem", "clean.plugmem")
print(report.kept, report.dropped_text, report.dropped_vector, report.dropped_metadata)

It reads the source fact by fact, writes what survives to a new file, and reports what it had to drop. The source is left untouched as evidence. This is not a repair for structural damage: a snapshot that will not parse cannot be walked, and that case is a restore from backup.

The one thing the Rust library has and this does not

import is not an engine verb — JSONL is a format the CLI defines. If you need it, remember_many plus link is the whole of it, in a dozen lines of Python you can shape to your own file.

Errors

Every failure this binding decides raises a subclass of PlugmemError carrying a stable code. The codes are the same strings the Node binding puts on a thrown Error, so cross-language documentation stays one table.

try:
    db = plugmem.Plugmem.open("agent.plugmem")
except plugmem.LockedError as e:
    print(e.code)          # PLUGMEM_LOCKED — another process holds the writer

Class	`code`	Means
`LockedError`	`PLUGMEM_LOCKED`	another process holds the writer lock
`NeedsCheckpointError`	`PLUGMEM_NEEDS_CHECKPOINT`	`read_only` on a database nobody has checkpointed
`ConfigError`	`PLUGMEM_CONFIG`	the `config.toml` could not be read or is invalid
`OpenError`	`PLUGMEM_OPEN`	any other failure to open
`InvalidArgError`	`PLUGMEM_INVALID_ARG`	an argument refused before it reached the engine
`InvalidNameError`	`PLUGMEM_INVALID_NAME`	not a usable memory name
`ClosedError`	`PLUGMEM_CLOSED`	`close()` was already called
`ReadOnlyError`	`PLUGMEM_READ_ONLY`	a write verb on a read-only handle
`WriterOnlyError`	`PLUGMEM_WRITER_ONLY`	`generation`/`refresh` on a writer
`BusyError`	`PLUGMEM_BUSY`	another operation holds this handle
`EngineError`	`PLUGMEM_ENGINE`	the engine failed; the message is its own

Configuration and embeddings

Without a config, plugmem answers from text, tags, the graph and time. Add an [embedder] section and remember/recall also embed, giving the vector source something to work with — see Do you need an embedder? for the trade.

The file is resolved the same way on every surface — CLI, MCP server, Node and Python: an explicit path, then $PLUGMEM_CONFIG, then $XDG_CONFIG_HOME/plugmem/config.toml.

# plugmem.toml
[database]
path = "~/.local/share/plugmem/agent.plugmem"

[engine]
dim = 1536

# Optional. Delete this section and everything still works, minus the vector
# source.
[embedder]
kind = "openai"
url = "https://api.openai.com/v1/embeddings"
model = "text-embedding-3-small"
api_key_env = "OPENAI_API_KEY"

[recall]
w_bm25 = 1.0        # weight of the lexical source
w_vec = 1.0         # weight of the vector source
w_graph = 0.7       # weight of the graph source
half_life_days = 30 # how fast the recency boost decays
graph_depth = 2     # default hops, overridable per call

db = plugmem.Plugmem.open("agent.plugmem", config="plugmem.toml")

plugmem.settings_help() returns the whole catalogue — every section, key, type, default and what it does — without opening anything.

When a key is misspelled

A typo in a key used to change nothing, silently. Now it is reported:

db = plugmem.Plugmem.open("agent.plugmem", config="plugmem.toml")
for warning in db.config_warnings():
    print(warning)
# [recall] unknown key `w_vector` — did you mean `w_vec`?

It is a value rather than a printed warning because a library has nowhere sensible to print. Read it once after opening and log it your own way.

Threads and the GIL

Every verb releases the GIL for the duration of the work. While a recall is inside the engine no bytecode executes on that thread's behalf, so the interpreter is free and other threads run.

That is why the API is synchronous and has no async def. The thing an async API would buy — not blocking everything else — is already true:

import asyncio

res = await asyncio.to_thread(db.recall, "tokio", k=5)

to_thread works correctly here because the GIL is released. An async layer would add a runtime and a scheduler to reach the same place.

A handle is safe to share across threads. Reads genuinely overlap; refresh and close take the handle exclusively, so a reader never observes it half-swapped.

from concurrent.futures import ThreadPoolExecutor

with ThreadPoolExecutor(max_workers=8) as pool:
    results = list(pool.map(lambda q: db.recall(q, k=4), queries))

Writes serialize inside the engine, which is a property of the engine and not of this binding — one writer per file is the design. Embedding happens outside that lock, so several remember calls do reach the provider at once.

Reading while another process writes

reader = plugmem.Plugmem.open("agent.plugmem", read_only=True)
print(reader.generation())      # which published snapshot this is
if reader.refresh():            # move to the newest one
    print("moved to", reader.generation())

A read-only handle maps a published snapshot without taking the writer's lock, so it coexists with a live writer in another process. It needs the database to have been checkpointed at least once; otherwise NeedsCheckpointError.

Typing

The package ships py.typed and generated stubs, so an editor completes the API and a type checker checks it. The stubs are generated from the same macros the binding is written with and gated in CI against the Rust surface, so they cannot describe a method that does not exist.

res: plugmem.RecallResult = db.recall("tokio", k=5)
first: plugmem.RecalledFact = res.facts[0]

Results are frozen: they are what the engine said, and mutating a copy of that is never what anyone means.

Many memories in one directory

Optional. If you want one memory, point Plugmem.open at a file and skip this.

For a process serving many independent memories — one per conversation, per tenant, per project — address them by name instead:

ws = plugmem.Workspace("~/bot-data")

db = ws.open("conversation-42")            # first use creates it
db.remember("the user prefers dark mode", entity="user")

ws.describe("conversation-42", "support thread about billing", owner="ann")
for entry in ws.find("billing"):
    print(entry.db, entry.description)

A name ([a-z0-9][a-z0-9_-]*) is not a path and cannot become one, so it resolves to exactly one database inside the directory. describe is what makes find useful when the caller does not know the name; owner is recorded as an edge, so find("ann") returns what Ann owns even though no description mentions her.

The workspace keeps a bounded pool of open memories and closes the least recently used to make room. close_idle() closes those idle past the configured timeout, which matters because an open memory holds that database's exclusive lock.

What it is not for

plugmem is for local-first application and agent memory: one process, one local database, no service to operate. Its design centre is around 100 000 active facts on one machine, and the benchmarks track 1M-operation profiles to show how the same engine behaves under heavier local load.

It is not a vector database and not built for multi-million vector workloads, cluster sharding, multi-tenant serving or managed nearest-neighbour search. For those, use a dedicated system — Qdrant, Milvus, Weaviate, Pinecone or pgvector.

Other ways in

The same engine ships five ways. This package is the Python one.

You are	Use
writing Python	this package
writing JavaScript / TypeScript for Node	`plugmem` on npm
writing Rust	`plugmem-host` — the engine in your process
an agent, or another language	`plugmem-mcp` — a stdio JSON-RPC sidecar
a person at a terminal	`plugmem-cli`

Working with an LLM agent? There is a companion skill describing the remember/recall loop, the contradiction workflow and the verbs. This package ships it: skill() returns the text and skill_version() the version it was written against.

License

MIT. Source: https://github.com/m62624/plugmem

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

plugmem-0.7.0-cp314-cp314t-win_arm64.whl (3.9 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tWindows ARM64

plugmem-0.7.0-cp314-cp314t-win_amd64.whl (3.9 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tWindows x86-64

plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.3 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tmanylinux: glibc 2.17+ x86-64

plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tmanylinux: glibc 2.17+ ARM64

plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl (4.1 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tmacOS 11.0+ ARM64

plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl (4.2 MB view details)

Uploaded Aug 5, 2026 CPython 3.14tmacOS 10.12+ x86-64

plugmem-0.7.0-cp310-abi3-win_arm64.whl (3.9 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+Windows ARM64

plugmem-0.7.0-cp310-abi3-win_amd64.whl (3.9 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+Windows x86-64

plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.4 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+manylinux: glibc 2.17+ x86-64

plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl (4.4 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+manylinux: glibc 2.17+ ARM64

plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl (4.1 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+macOS 11.0+ ARM64

plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl (4.2 MB view details)

Uploaded Aug 5, 2026 CPython 3.10+macOS 10.12+ x86-64

File details

Details for the file plugmem-0.7.0-cp314-cp314t-win_arm64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-win_arm64.whl
Upload date: Aug 5, 2026
Size: 3.9 MB
Tags: CPython 3.14t, Windows ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-win_arm64.whl
Algorithm	Hash digest
SHA256	`b112ecd4a1a433dbaa9d9a207445a6b9f09853da24664b00c5f5eeab50295bfc`
MD5	`df3841b82873b824f818e9e42c4208c0`
BLAKE2b-256	`f583a70371ef43293c79dea9466ef60aa95191d6f299d54bb38997cba7e2aadc`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-win_arm64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-win_arm64.whl
- Subject digest: b112ecd4a1a433dbaa9d9a207445a6b9f09853da24664b00c5f5eeab50295bfc
- Sigstore transparency entry: 2349073420
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp314-cp314t-win_amd64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-win_amd64.whl
Upload date: Aug 5, 2026
Size: 3.9 MB
Tags: CPython 3.14t, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-win_amd64.whl
Algorithm	Hash digest
SHA256	`f91f64279d22786ac18a6e573972ae01e717bc5e2d5dd5d8461e0284cef356ab`
MD5	`9556b61dfec70e2ae413dc81cd282f3e`
BLAKE2b-256	`4de42d7bf0551c3496d37036217047caa67966b522408dd809cc2c5b4e5e7aed`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-win_amd64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-win_amd64.whl
- Subject digest: f91f64279d22786ac18a6e573972ae01e717bc5e2d5dd5d8461e0284cef356ab
- Sigstore transparency entry: 2349071973
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Aug 5, 2026
Size: 4.3 MB
Tags: CPython 3.14t, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`a1232903e321ae6a5fbf516ca16f91e9a37b5b5186c7bf2afb99ab124111d4c7`
MD5	`2ef200d101815b5994cbbe5deaa5292f`
BLAKE2b-256	`d6cdd884ce2e07f9d3aae01af04be17798ddacceb11192b36e482dcd4252103e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: a1232903e321ae6a5fbf516ca16f91e9a37b5b5186c7bf2afb99ab124111d4c7
- Sigstore transparency entry: 2349072477
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Upload date: Aug 5, 2026
Size: 4.4 MB
Tags: CPython 3.14t, manylinux: glibc 2.17+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm	Hash digest
SHA256	`a48d2dfc2fa8edd1a4a2284a03f72ba3341a4d98739e1a16101b8fb2d99118ad`
MD5	`327860de4690d29730ea369e8cf230c1`
BLAKE2b-256	`7fe2244a02f19a1f737dd8a6833674912d619aafbaf7c058e3f11a5cac81a59f`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
- Subject digest: a48d2dfc2fa8edd1a4a2284a03f72ba3341a4d98739e1a16101b8fb2d99118ad
- Sigstore transparency entry: 2349074125
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl
Upload date: Aug 5, 2026
Size: 4.1 MB
Tags: CPython 3.14t, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`d042180229b7b5b70f8a8719c9fab723ddd3f6c6b3c2629d80dd9a1870fd7511`
MD5	`e04fca12a41db6e7483b8acebdb51d78`
BLAKE2b-256	`3f34b72a58408704ce60f7b340dfd3c648a804286f664806d8cbf9322b8e3fb9`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-macosx_11_0_arm64.whl
- Subject digest: d042180229b7b5b70f8a8719c9fab723ddd3f6c6b3c2629d80dd9a1870fd7511
- Sigstore transparency entry: 2349071874
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl.

File metadata

Download URL: plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl
Upload date: Aug 5, 2026
Size: 4.2 MB
Tags: CPython 3.14t, macOS 10.12+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl
Algorithm	Hash digest
SHA256	`0eeb811fbd6df954572ed232e7b50b312d743776075030615bab5e0b776619db`
MD5	`c89a1db5255090c3f829db71c7530074`
BLAKE2b-256	`0779132f05423d856ac647829a0c4d15a953a8d3307188a63d1338e498a9eb1e`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp314-cp314t-macosx_10_12_x86_64.whl
- Subject digest: 0eeb811fbd6df954572ed232e7b50b312d743776075030615bab5e0b776619db
- Sigstore transparency entry: 2349073155
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-win_arm64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-win_arm64.whl
Upload date: Aug 5, 2026
Size: 3.9 MB
Tags: CPython 3.10+, Windows ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-win_arm64.whl
Algorithm	Hash digest
SHA256	`fe01b68cc602080ec9eb695e6ea5b69bfbe877ed00bac9529b625a6be6737d1a`
MD5	`aa5b4ad88751e072edfa645cbc249c1e`
BLAKE2b-256	`82c3c4ed6613809d9208251200192ff84033ec34eb086d81a7bf83cf02d258df`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-win_arm64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-win_arm64.whl
- Subject digest: fe01b68cc602080ec9eb695e6ea5b69bfbe877ed00bac9529b625a6be6737d1a
- Sigstore transparency entry: 2349072278
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-win_amd64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-win_amd64.whl
Upload date: Aug 5, 2026
Size: 3.9 MB
Tags: CPython 3.10+, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-win_amd64.whl
Algorithm	Hash digest
SHA256	`0148d320d7a44b2011b845cdca7d006f993ed904ce77c34b7d6dff7b4bddd27c`
MD5	`89afea7e8513ef5cd64fa4a9fecec859`
BLAKE2b-256	`70d030608892ddca30aa719097a3ef2d7a96ad8e2d7325116348b749fcd19fb3`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-win_amd64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-win_amd64.whl
- Subject digest: 0148d320d7a44b2011b845cdca7d006f993ed904ce77c34b7d6dff7b4bddd27c
- Sigstore transparency entry: 2349071761
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Upload date: Aug 5, 2026
Size: 4.4 MB
Tags: CPython 3.10+, manylinux: glibc 2.17+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`17afca0a00fb9bdd30b0d704ac4bd6c3a672031ccf3fdce65476b97579a1cb0e`
MD5	`2ee6af54b1a6f71fe497ed38dad54859`
BLAKE2b-256	`da73a4e9faeb8107ab74eee51cc5c6f77e66ee2f24086e53a311dc691877c6d1`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
- Subject digest: 17afca0a00fb9bdd30b0d704ac4bd6c3a672031ccf3fdce65476b97579a1cb0e
- Sigstore transparency entry: 2349073687
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Upload date: Aug 5, 2026
Size: 4.4 MB
Tags: CPython 3.10+, manylinux: glibc 2.17+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
Algorithm	Hash digest
SHA256	`5a4db1cbc58f3096c8a72e4d0c5156961fbd76b181a06ba5ccb65bfa6e319f34`
MD5	`f52e69e02d1f09252e7a07bb19f99e64`
BLAKE2b-256	`194ec75b347402b6907845b6afffce105bf397e3b077a8238c9ab17fd59b09ee`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
- Subject digest: 5a4db1cbc58f3096c8a72e4d0c5156961fbd76b181a06ba5ccb65bfa6e319f34
- Sigstore transparency entry: 2349073898
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl
Upload date: Aug 5, 2026
Size: 4.1 MB
Tags: CPython 3.10+, macOS 11.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl
Algorithm	Hash digest
SHA256	`3e47fdcb478bc18126b2607535bbafa14d52ca1c00cb61721a31915f11052e4a`
MD5	`222ed3deca9fe78cc2338c4dabbbda64`
BLAKE2b-256	`0b7d63d812e3c9de7572c7c06a3fde5af5026425f49f088ce7abed9afc83a3b2`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-macosx_11_0_arm64.whl
- Subject digest: 3e47fdcb478bc18126b2607535bbafa14d52ca1c00cb61721a31915f11052e4a
- Sigstore transparency entry: 2349074316
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

File details

Details for the file plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl.

File metadata

Download URL: plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl
Upload date: Aug 5, 2026
Size: 4.2 MB
Tags: CPython 3.10+, macOS 10.12+ x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl
Algorithm	Hash digest
SHA256	`33af0e8dbe6edb8e9fc448e9d16786a11e58a44879413bb2c1033d8ec7ba39b1`
MD5	`525a5381139e0ad2eed668de8981ec2a`
BLAKE2b-256	`2039cac29609a4d8fecd5853ad69cb3b1a30eabb358d7758a3211b4c476a7f14`

See more details on using hashes here.

Provenance

The following attestation bundles were made for plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl:

Publisher: release.yml on m62624/plugmem

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: plugmem-0.7.0-cp310-abi3-macosx_10_12_x86_64.whl
- Subject digest: 33af0e8dbe6edb8e9fc448e9d16786a11e58a44879413bb2c1033d8ec7ba39b1
- Sigstore transparency entry: 2349072774
- Sigstore integration time: Aug 5, 2026
Source repository:
- Permalink: m62624/plugmem@e007c614e443c99711e618e71b08a63c59196854
- Branch / Tag: refs/tags/pin/v0.7.0
- Owner: https://github.com/m62624
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: release.yml@e007c614e443c99711e618e71b08a63c59196854
- Trigger Event: push

Release history Release notifications | RSS feed

0.8.0

Aug 6, 2026

0.7.1

Aug 6, 2026

This release

0.7.0

Aug 5, 2026

plugmem 0.7.0

plugmem

Install

Quick start

Do you need an embedder?

What it stores

Two clocks

How recall works

API

Bringing your own embedding

Backing up: facts are only half of it

Checking a file has not rotted

Repairing a damaged file

The one thing the Rust library has and this does not

Errors

Configuration and embeddings

When a key is misspelled

Threads and the GIL

Reading while another process writes

Typing

Many memories in one directory

What it is not for

Other ways in

License

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License expression

Requires

Tags

Classifiers

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance