ai-memory architectures

A primitive that scales from one agent on a laptop to a global hive of millions. Every tier ships either today, or sits behind a documented gap with a known roadmap. Nothing on this page is marketing fiction — every "today" claim cites code in the v0.6.3 source tree.

5 tiers T1–T3 ship today T4 partial · v0.7 GA T5 vision · v1.0+
The five tiers

From single agent to global collective.

Each tier is a deployment pattern. Each inherits everything below it. Click a card for the full diagram, narrative, and deployment recipe.

Capability matrix

What ships today vs. what's on the road.

The honest matrix. Cell colors match the badges above.

Capability T1 T2 T3 T4 T5
SQLite-backed store, FTS5 keyword recall YES YES YES → pgvector → pgvector
Semantic recall (HNSW, MiniLM 384-dim) YES YES per-node shared idx shared idx
Namespace isolation + scope visibility (as_agent) n/a YES YES YES YES
Per-namespace governance policy n/a YES YES YES YES
Pending-approval gates (write/promote/delete) n/a YES YES YES YES
Knowledge-graph w/ temporal validity (v0.6.3) YES YES YES YES YES
Hierarchical taxonomy (memory_get_taxonomy) YES YES YES YES YES
Capabilities introspection v2 (v0.6.3) YES YES YES YES YES
One-way sync_push fanout (memories, links, governance, pending) n/a n/a YES YES YES
Vector-clock causality (sync/since) n/a n/a YES YES YES
Quorum-write contract (W-of-N peer ack) n/a n/a YES YES YES
mTLS peer mesh + fingerprint allowlist n/a n/a YES YES YES
Postgres + pgvector backend feature flag feature flag feature flag GA · v0.7 GA · v0.7
Cryptographic agent attestation (signature field) field reserved v0.7 v1.0+
Distributed consensus (Raft / Paxos) v1.0+
Gossip / DHT for many-node discovery scoped required
Composition

Why a layered architecture story.

ai-memory is a primitive, not a platform. The same Rust binary, the same data model, the same MCP protocol surface scales from a developer's ~/.claude/ai-memory.db to a fleet running across racks. What changes between tiers:

What stays the same:

Every tier inherits everything below it.

Federation primitives

What lives in the codebase today.

These are the building blocks every multi-node tier composes. All shipped, all in v0.6.3:

How to read

Each tier page contains.

  1. An animated SVG diagram showing memory data flow — writes, recalls, peer sync, governance gates, and (where relevant) attestations.
  2. A "what's actually happening" narrative walking the reader through a recall and a write.
  3. Capability badges on every primitive — cyan ships today, orange partial, purple roadmap, pink future vision.
  4. A deployment recipe with real commands.
  5. Governance, skills, and attestations wiring for the tier — what enforces the rules at this scale.
  6. Honest limits — what would break, and at what scale.

Start at Tier 1 and walk forward, or jump straight to the tier that matches your fleet.

Engineering honesty. Every "ships today" claim cites a file path and behavior in the v0.6.3 source tree. Roadmap items reference ADRs and tracked work. The vision tier (T5) is the north star — we'll get there, but it's not shipping in v0.7. If a diagram shows something the code doesn't do, that's a documentation bug — please file an issue.