cortexm remembers what you tell it. Forever. For free. On your machine. Same result every time.

Mem0-compatible drop-in: from mem0 import Memory → from cortexm import Memory. Zero LLM calls at ingest. Zero LLM calls at retrieval. Zero monthly cost. Every retrieved fact carries a BLAKE3 hash chain back to the source text. One .db file you own.

Quick start

pip install cortexm          # works offline, no API keys, single command

from cortexm import Memory   # Mem0-compatible surface

m = Memory()
m.add("I work at Google", user_id="alice")
m.search("Where does Alice work?", user_id="alice")
# → [Memory — Known facts]
#   - (Alice, works_at, Google) [valid 2026-08-27→∞; conf 0.92;
#      id 3f2a91c2; src #a1b2c3d4; "I work at Google"]

Canonical LongMemEval — μ=0, $0, on a 4GB laptop

Full 500-question results (v0.6.2 baseline; v0.6.4 re-run lands the experimental graph-recall + coherence modules below):

Baseline beaten: v0.5.5 baseline was 0.948; this is a +2.6 pp improvement on the full 500-question corpus.

Known remaining gaps (diagnosed, not guessed):

• Temporal anchoring — degrades on multi-week relative references ("four weeks ago", "10 days ago"). These 6 failures connect to the temporal_chain_notes / supersession-history mechanism in reader.py. v0.6.4's cortexm/experimental/coherence.py adds a deterministic temporal-coherence rerank signal aimed at exactly these.
• Arithmetic aggregation — the generalized sum_or_diff judge (v0.6.2) fixes the 2–3 real computation gaps. The remaining multi_session failures are retrieval misses (wrong session pulled: poetry instead of podcasts, marketing facts instead of video views), not judge failures. v0.6.4 wires the previously-dead percentage/numeric_agg judges and adds cortexm/experimental/graph_recall.py (entity-adjacency 2-hop walks) aimed at the wrong-session misses.
• BOOL strategy at 85.7% is the weakest category — needs sign-of-evidence refinement for edge cases.

Run the full 500-Q benchmark via GitHub Actions: .github/workflows/longmemeval.yml (20 shards, ~30s/q with per-shard DB caching).

Known boundaries (the short list)

Full detail: docs/FAILURE_MODES.md — every failure tied to a public benchmark question.

1. The extractor is a 61-pattern lookup, not a language model. Phrasings outside the pattern library are silently dropped at ingest (e.g. "Anna has a cat named Whiskers") — they remain retrievable via verbatim/BM25 chunk recall, but never become structured facts. This is the price of μ=0: no generativity, no fabrication, no drift.
2. ZK proofs are trusted-prover attestations. The v0.6.4 backend (Pedersen + Sigma protocols on secp256k1) is sound at the commitment layer — challenges are bound to announcements, both OR-proof branches verify, H has no known discrete log, thresholds are enforced — but the linkage between committed values and store rows is established at prove-time by the prover. Verify the integration layer before trusting it against a malicious host.
3. Set membership reveals the leaf index. The value stays hidden (random-blinding Pedersen + equality proof); the position in the set does not. Position-hiding needs a ZK-friendly Merkle construction — documented future work.
4. No cross-user inference, ever. Every fact is scoped by user_id; the scope sandbox turns empty scopes into empty results (not unrestricted fallbacks). This is a feature, and it also means no "insight across users" stories.
5. Compression tiers are documented, not default. int8/binary quantization trade recall for space (see docs/COMPRESSION.md); the default build keeps full-precision embeddings because the benchmark headroom doesn't justify the loss yet.
6. Judge coverage is rule-based. The deterministic judge answers via strategy dispatch (bool/list/nugget/sum_or_diff/percentage/numeric_agg/holiday/paren). Questions outside those strategies score 0 even when retrieval succeeded — the failure is honest, the number is real.

When to use cortexm vs Mem0 / Zep / Chroma

• Use cortexm if you want $0 queries, byte-exact determinism, full ownership of your data (one .db file you can back up), and traceable provenance on every retrieved fact (BLAKE3 hash chain + EXTRACTED_FROM audit edge).
• Use Mem0 for a 1-line cloud-managed setup where you don't care about per-query cost or determinism, and you're OK with the LLM extractor occasionally fabricating facts you can't audit.
• Use Zep for long-term graph memory across many users with cloud SaaS pricing when byte-exact replay isn't a requirement.
• Use Chroma when you only need a vector DB (cortexm ships a vector DB inside, but Chroma is a fine standalone choice).

Drop-in plugins (already shipped)

• Mem0-compatible surface: from cortexm import Memory — drop-in for from mem0 import Memory
• LangChain: plugins/langchain → context-m-langchain on PyPI
• LlamaIndex: plugins/llamaindex → postprocessor
• OpenAI Agents SDK: plugins/openai_agents
• Claude Code: plugins/context-m-claude — session lifecycle hooks
• MCP server: cortexm serve (stdio JSON-RPC, zero extra dependencies)
• REST server: cortexm serve-rest — OpenAPI 3.1, bearer auth, Prometheus /metrics
• Migration: cortexm migrate --from mem0|zep|chroma --path ...

Documentation

The README is intentionally short. Everything else lives in docs/:

Examples & tests

• examples/ — runnable scripts, offline, no API keys (01_quickstart → 20_agent_session)
• tests/ — 698 tests: fabric + enterprise + PPR + concurrency + sandbox + enrichment + WAL crash-recovery + migration + CRDT federation + Rust parity + ZK soundness/forgery + public-API smoke
• cortexm/experimental/ — deterministic research borrows (graph recall, coherence) — μ=0 or it doesn't ship
• leaderboard/ — self-hosted benchmark site (rebuild: python leaderboard/build.py; open leaderboard/index.html)
• AGENTS.md — how AI coding agents should interact with this repo (2026 standard)
• CONTRIBUTING.md — contribution guide

License

Apache 2.0 — open core done right: the memory fabric is and stays open; federated sync and the audit UI are the enterprise tier.