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.
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.
| Field | Value | Source of truth |
|---|---|---|
| Current release | v0.6.3 | git tag v0.6.3 on main · cut 2026-04-24 |
| Test count (total) | 1,809 | 1,600 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) | 1,600 | Library tests only — Tier 1 PASS row, "1 600/1 600 lib tests pass" |
| Test coverage | 93.08% | 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) | 43 | Counted from tool_definitions() in src/mcp.rs |
| HTTP endpoints (unique routes) | 42 | Counted from .route(...) calls across handlers.rs + federation.rs + lib.rs |
| CLI commands | 26 | Counted from the Command enum + dispatch in src/main.rs |
| CI matrix platforms | 3 | ubuntu-latest · macos-latest · windows-latest — see .github/workflows/ci.yml |
| LongMemEval Recall@5 | 97.8% | 489/500 questions · ICLR 2025 benchmark · pure SQLite FTS5+BM25 · zero cloud — see performance.html |
| Schema version | v15 | v0.6.3 KG temporal-validity migration · see schema.html |
grep #[test] includes attributes inside #[cfg(test)] guards that are not always compiled, plus benchmark scaffolding — it is not the canonical test-pass count.
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.
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.
Adaptive blend, cross-encoder rerank, recency decay, tier boost. 97.8% Recall@5 on LongMemEval (ICLR 2025).
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.
Allow / Deny / Pending policies; pending-approval queue; scope-visibility filter; immutable agent_id provenance. v0.6.2+ stable.
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.
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.
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.
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.
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.
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.
| Certification | Status | Authority |
|---|---|---|
| A2A-Certified (internal) | Yes | A2A gate · v0.6.2 + v0.6.3 |
| Ship-Gate (internal) | Yes | Ship gate · 9/9 cert + 5/5 channels green at v0.6.2 cut |
| SOC 2 | No | No third-party audit. Do not represent. |
| ISO 27001 | No | No third-party audit. Do not represent. |
| FedRAMP | No | No authorization. Do not represent. |
| HIPAA | No | No BAA. Do not represent. |
test-hub/releases/vX.Y.Z/.docs/evidence.html first — the hero FROZEN badge, every row of the facts table, and every status card whose maturity has changed.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.