io.github.writerslogicPublished by GitHub account writerslogicv0.1.5Updated Nov 7, 2026
Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage.
Local persistent memory for AI assistants: store, recall, search, export and delete durable facts and preferences in an on-disk store.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
WritersLogic Adaptive Retention & Memory.
Hybrid search, graph indexing, and vector-symbolic memory.
Local memory for agents and apps: full-text and vector search, a memory API and a vector-symbolic fact store in one embeddable Rust engine that makes no network calls.
[CI] [MSRV 1.89] [OpenSSF Scorecard] [OpenSSF Best Practices] [License: Apache-2.0] [WARM MCP MCP server – quality and maintenance score on Glama]
[Bemula forgetting score, DeepSeek backbone] [LongMemEval dev, gpt-4o reader and judge] [VIBE llama-128-ip max recall@100, one thread]
Website · Docs · Get started · Standards and provenance · Results · Capabilities · Limits · Contribute
WARM is a Rust library that stores text, vectors and facts in a directory on your machine and finds them again. It ships with Node.js bindings, C, WASM and UniFFI bindings, an HTTP server with a Python client, and an MCP server. There are no service calls, no telemetry and no model downloads unless you turn on a feature that asks for one.
Every row links to the committed file it comes from. These are single machines and stated protocols, not a substitute for testing your own data.
Method, intervals and every loss: docs/benchmarks and the benchmarks pages.
Generated from benchmarks/results/competitive/ by warm-bench table; method and caveats in docs/benchmarks/COMPARISON.md. W = WARM ahead (95% interval excludes parity), T = tie, L = a comparator is ahead, - = no verdict (unpinned source revision, no interval, or not comparable). Rows are compared only within one machine.
Clone once: git clone https://github.com/writerslogic/warm && cd warm.
Run the offline agent-memory demo with cargo run --release --example demo-offline-agent.
From your own Rust project, add the current Apache-2.0 source:
The historical v0.6.1 source
remains AGPL-3.0-or-later; it is available from that Git tag, not as a
warm-rust 0.6.1 release on crates.io.
Unreleased Rust API change: WarmCore::query, query_batch, and
analyze_components return Result. Handle the result with ? or an explicit
error branch; deferred-encoding failures no longer become successful partial
query results. get_document, list_documents, get_document_info, and list_document_info
also return Result; retained-text and checkpoint decoding failures propagate
instead of panicking, and reads no longer hydrate the
entire checkpoint or hold store locks during text I/O.
Install the Node.js package and its platform-specific native binary:
To build from source, run npm ci --omit=optional && npm run build with Rust installed.
The WARM release includes listDocuments for scoped pruning. See the
integration guide for source
provenance, namespace isolation, dry runs and deletion limits.
The Python package warm-sdk is an HTTP client for warm-server, which stores vectors you
supply. (warm-python provides native vector search and phase vectors, but no document search.)
Endpoints, flags, tenants and limits are in the
server docs. A runnable Python quickstart
with a toy embedder is in examples/quickstart/python.
warm-mcp serves a store to any Model Context Protocol client over stdio or HTTP:
The MCP package is a separate launcher. To build the server from source:
Client setup, data directory and the one-writer rule: MCP integration.
For normalized content from multiple applications, see the organizational knowledge adapter.
The five-minute quickstart
walks through ingest, search, a SQLite FTS5 comparison and encryption in Rust, Python and Node,
and CI runs that code on every pull request. For a whole agent memory with no embeddings and no
network, run cargo run --example demo-offline-agent.
Every capability above except document search and the vector index is behind a Cargo feature or runtime option that is off by default; Cargo features lists them all.
Module map: docs/ARCHITECTURE.md.
storeText: false keeps term counts, IDs and
embeddings, so it is not a privacy control.WarmCore::new(.., None, ..) uses the current directory.Full statement: docs/PRIVACY.md. Report vulnerabilities privately via SECURITY.md.
CONTRIBUTING.md: setup, the checks CI runs, DCO sign-off (git commit -s, no
CLA). Start with a good first issue
or Discussions. See the
Code of Conduct. Benchmark changes regenerate the results file they touch;
the README cites files, not remembered figures.
Apache-2.0. See LICENSE. Use, modify and embed it in open-source or proprietary software, including network services, with no copyleft obligation. The historical v0.6.1 source remains available under its AGPL-3.0-or-later license.
Source: README.md at commit af8d401
Store memory
Store a durable fact, decision or preference; use `recall` to find one instead. Omit `id` to create a memory; an existing `id` replaces its text, title, tags and metadata, clearing optional fields you omit. Use `if_version` with a known id to reject concurrent changes, or `create_only` to reject overwrites.
idtagstextrequiredtitlemetadataif_versionallow_emptycreate_onlyRecall matching memories
Retrieve full memories ranked for a natural-language question. `tags` require every listed label, and `min_score` drops low relative-score matches; use `search` for exact metadata-key filters, custom ranking weights or fusion, or text previews instead of full memories. Read-only; ranking is lexical by default, with semantic ranking when a model is configured.
ktagsqueryrequiredmin_scoreSearch memory with filters
Find memories with metadata filters or ranking controls; use `recall` for simpler full-text answers. Read-only. Results contain text previews and relative ranking scores, not probabilities; use `get` to read a result in full. Semantic scores require a configured model.
ktagsqueryrequiredfilterfusionmin_scorelexical_weightsemantic_weightGet memory
Read one known memory id in full, including tags, metadata and version. Use an id from `list` or `search`; use `recall` when only a natural-language question is known. Read-only; an unknown id returns an error.
idrequiredDelete memories
Delete memories from the active store by exact id(s) or id prefix; use `remember` to update content instead. Deletion has no undo: inspect prefix matches with `list` first and set `confirm: true` for prefix deletion. Exact ids and a prefix cannot be combined, and a batch failure may leave earlier ids deleted.
ididsprefixconfirmList memories
Browse memories in id order, optionally limited by id prefix or tag; use `search` for relevance ranking. Read-only. Returns text previews unless `full` is true; pass `next_cursor` as `cursor` to continue.
tagfulllimitcursorprefixStore statistics
Inspect store counts, recall mode, encryption status, storage size and active limits without reading memory contents. Read-only; use `list` to inspect stored memories.
Takes no parameters.
Export memory contents
Export a portable copy of many memories as JSON, JSONL or Markdown. Use `get` for one known memory, `recall` or `search` to find matches, and `list` for short previews. The text payload is capped by the export byte limit; pass `next_cursor` as `cursor` for more. Pages read the live store, so concurrent writes can change later pages.
taglimitcursorformatprefix90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
cargo add warm-rustuse writerslogic_warm::{DocumentInput, WarmCore, SearchOptions};
let dir = tempfile::tempdir()?;let warm = WarmCore::new(4096, Some(dir.path().display().to_string()), None)?;warm.memorize_document(DocumentInput { id: "backups".into(), text: "Restore deleted documents from verified backups.".into(), source_uri: Some("operations.md".into()), version: Some("1".into()), metadata: Some(serde_json::json!({ "project": "alpha" })), chunk_words: None, overlap_words: None, store_text: None, embeddings: None, title_weight: None,})?;let hits = warm.search_documents("restore backups", &SearchOptions::default())?;println!("{} {:?}", hits[0].document_id, hits[0].source_uri);npm install warm-sdkconst { WarmMemorySystem } = require('warm-sdk')const { DocumentMemory } = require('warm-sdk/semantic')
async function main() { const dir = require('node:fs').mkdtempSync(require('node:path').join(require('node:os').tmpdir(), 'warm-readme-')) const memory = new DocumentMemory(new WarmMemorySystem(4096, dir)) await memory.memorize({ id: 'backups', text: 'Restore deleted documents from verified backups.', sourceUri: 'operations.md', version: '1', metadata: { project: 'alpha' }, }) const [hit] = await memory.search('restore backups', { filter: { project: 'alpha' } }) console.log(hit.documentId, hit.sourceUri, hit.text) await memory.flush()}main().catch(error => { console.error(error); process.exit(1) })cargo build --release --features server --bin warm-serverWARM_API_KEY=change-me target/release/warm-server --input-dim 384 &uv pip install warm-sdkfrom writerslogic_warm_sdk import WarmClient
client = WarmClient(url="http://127.0.0.1:8080", api_key="change-me", tenant_id="demo")client.add_documents([{"id": "a", "vector": [0.1] * 384, "text": "hello", "metadata": {}}])print(client.query([0.1] * 384, top_k=1)["matches"][0]["id"])npx -y writerslogic-warm-mcp # stdio; downloads a verified binary on first runnpx -y writerslogic-warm-mcp --transport http # http://127.0.0.1:8765/mcpcargo build --release --features mcp,security --bin warm-mcp # add local-models for semantic recall./target/release/warm-mcp # stdio./target/release/warm-mcp --transport http # http://127.0.0.1:8765/mcpflowchart TB subgraph bindings["Bindings and servers"] rust["Rust crate"] node["Node.js (napi)"] ffi["C, WASM, UniFFI"] python["Python: warm-sdk"] server["warm-server (HTTP)"] mcp["warm-mcp (stdio, HTTP)"] end subgraph engine["Engine API"] core["WarmCore: documents, vectors, facts, mutation gate"] prov["Security and provenance: signed audit log, COSE/SCITT"] end subgraph indexes["Indexes and memory"] text["Text index: blocked postings, BM25, Boolean and phrase"] vector["Vector index (qgraph): vertex file, updatable delta, query-aware projection"] memory["Memory API: remember, recall, forget, conversation memory"] vsa["Vector-symbolic layer: bind, bundle, Hopfield cleanup"] end subgraph storage["Storage"] journal["Journal and checkpoints"] segments["Append-only segments (CRC32, LZ4)"] mapped["Memory-mapped files"] crypto["AES-256-GCM encryption (optional)"] end python --> server rust --> core node --> core ffi --> core server --> core mcp --> core core --> text core --> vector core --> memory core --> vsa core --> prov memory --> text text --> journal vector --> journal memory --> journal journal --> segments segments --> mapped segments --> crypto