FROZEN · v0.6.3 · 2026-04-24

The single source of truth.

Every public page about ai-memory — README, marketing site, roadmap, architecture pages, sales decks — must source its numbers from this page or from the upstream test-hub evidence it cites. No other page invents its own counts. If a number on another page disagrees with this page, this page is correct and the other is a bug — please file an issue.

🧪 Live test-hub → 📊 v0.6.3 release evidence → 🚢 ship-gate 🤝 A2A-gate
Frozen facts · v0.6.3

The numbers.

All values below are taken from the v0.6.3 release evidence published on the test-hub, or counted directly from the v0.6.3 source tree. Source links accompany each row.

FieldValueSource of truth
Current releasev0.6.3git tag v0.6.3 on main · cut 2026-04-24
Test count (total)1,8091,600 lib (cargo test --lib) + 209 integration (cargo test --tests). Tier 1 row of the v0.6.3 evidence page — "1 600/1 600 lib tests pass" plus integration suite
Test count (lib only)1,600Library tests only — Tier 1 PASS row, "1 600/1 600 lib tests pass"
Test coverage93.08%Tier 1 row of the v0.6.3 evidence page · cargo llvm-cov · gate ≥92% · release-cut measurement was 93.05% (within rounding of most-recent 93.08%)
MCP tools (unique)43Counted from tool_definitions() in src/mcp.rs
HTTP endpoints (unique routes)42Counted from .route(...) calls across handlers.rs + federation.rs + lib.rs
CLI commands26Counted from the Command enum + dispatch in src/main.rs
CI matrix platforms3ubuntu-latest · macos-latest · windows-latest — see .github/workflows/ci.yml
LongMemEval Recall@597.8%489/500 questions · ICLR 2025 benchmark · pure SQLite FTS5+BM25 · zero cloud — see performance.html
Schema versionv15v0.6.3 KG temporal-validity migration · see schema.html
Note on test-count framing. Public materials should lead with the 1,809 total tests figure (1,600 lib + 209 integration); the 1,600 lib-only number remains exposed as the test-hub Tier 1 row "1 600/1 600 lib tests pass" for procurement teams who want to see library-test isolation. Older pages may reference 191 tests (~v0.6.0 era) — those are stale and should be replaced. The 1,898 figure from a raw grep #[test] includes attributes inside #[cfg(test)] guards that are not always compiled, plus benchmark scaffolding — it is not the canonical test-pass count.
Maturity

What is production-ready, what is not.

This is where conflicting maturity signals on other pages get resolved. Use these labels — and only these labels — when describing capability maturity in any public material.

Production-ready

Single-node operation

One ai-memory instance, one consumer. SQLite + WAL + FTS5 + HNSW. No network, no peers. Used in production by the project team daily. T1 + T2 of the architectures matrix.

Production-ready

Hybrid recall (FTS5 + semantic)

Adaptive blend, cross-encoder rerank, recency decay, tier boost. 97.8% Recall@5 on LongMemEval (ICLR 2025).

Production-ready

MCP + HTTP + CLI surface

43 MCP tools, 42 HTTP routes, 26 CLI commands. Stable contract. 1,809 tests passing (1,600 lib + 209 integration) at 93.08% line coverage. Used by Claude Code, Codex, Cursor, Windsurf, Continue.dev, Grok, OpenClaw, Hermes, and Llama integrations today.

Production-ready

Per-namespace governance

Allow / Deny / Pending policies; pending-approval queue; scope-visibility filter; immutable agent_id provenance. v0.6.2+ stable.

Beta

Federation — quorum writes (W-of-N)

Code shipped in v0.6.3: 10 broadcast functions, ack tracker, vector-clock catchup, mTLS fingerprint allowlist. Used in T3 (multi-node cluster) tests on the ship-gate. Not yet recommended for self-driving production fleets without an operator-on-call. See T3 architecture for what's wired and what's not.

Experimental

Postgres + pgvector backend

sal-postgres Cargo feature flag in v0.6.3. Schema-parity fixes shipping #294-#297. GA target: v0.7. Not for production until v0.7 ships.

Experimental

Smart / Autonomous tier (Ollama LLM)

Query expansion, auto-tagging, contradiction detection, cross-encoder reranking via Ollama (Gemma 4 e2b/e4b). Functional and tested but performance/quality varies by host hardware. Production use should pin model versions and run baseline recall regressions.

Unsupported (today)

Cryptographic agent attestation

The memory_links.signature field is reserved in schema v15 but not signed/verified by the binary today. agent_id today is claimed, not attested. Do not make security decisions on agent_id alone. Attestation lands in v0.7.

Unsupported (today)

Multi-region distributed consensus

No Raft, no Paxos, no global gossip/DHT. Tier 5 ("global hive") of the architectures matrix is vision — v1.0+ horizon. Don't deploy ai-memory across regions today expecting strong consistency.

Reconciling the "is not a distributed system" claim in ADMIN_GUIDE.md. The admin guide is correct in spirit and historically lagged the v0.6.3 federation work. The accurate v0.6.3 framing is: ai-memory is a single-machine primitive that ships beta-quality federation primitives (quorum writes, mTLS peer mesh, vector-clock catchup) for opt-in multi-node clusters (T3). It is not a distributed database. It does not provide strong consistency, distributed consensus, or self-healing global state. Operators choosing to run a federated cluster today must accept beta-quality replication and own their consistency guarantees at the application layer.
Certification

Current certification status.

ai-memory v0.6.3 holds the following internal certifications. External (third-party) audits and compliance attestations are not yet held for any release; do not represent ai-memory as SOC 2, ISO 27001, FedRAMP, or HIPAA-compliant.

CertificationStatusAuthority
A2A-Certified (internal)YesA2A gate · v0.6.2 + v0.6.3
Ship-Gate (internal)YesShip gate · 9/9 cert + 5/5 channels green at v0.6.2 cut
SOC 2NoNo third-party audit. Do not represent.
ISO 27001NoNo third-party audit. Do not represent.
FedRAMPNoNo authorization. Do not represent.
HIPAANoNo BAA. Do not represent.
Authoring rule

How to keep this page canonical.

  1. Cut a release tag.
  2. Run the full ship-gate matrix; publish a release evidence page at test-hub/releases/vX.Y.Z/.
  3. Update docs/evidence.html first — the hero FROZEN badge, every row of the facts table, and every status card whose maturity has changed.
  4. Sweep all references: grep -rE "(191|1,?[0-9]{3})\s*test|9[0-9]\.[0-9]+%\s*coverage|v0\.6\.[0-9]" docs/ README.md — every match either updates to the new canonical number or replaces with a link to evidence.html.
  5. Open one PR for the sweep. Block release until it merges.