agent-memory vs linearmemory
Neo4j Labs' graph-native agent memory: conversations, a POLE+O entity knowledge graph and reasoning traces in one store, with a 16-tool MCP server and hosted or self-hosted backends. — versus — Legible persistent agent memory: records observable execution events, consolidates only validated knowledge and explains every relation — MCP server on PostgreSQL 17 with a web explorer.
Both are graph-shaped agent memories with reasoning traces. Neo4j Labs' agent-memory is graph-native on Neo4j with a POLE+O entity model; LinearMemory keeps Postgres authoritative and derives the graph, with an explanation on every edge.
| agent-memory | linearmemory | |
|---|---|---|
| Stars | 522 | 1 |
| Forks | 99 | 0 |
| Language | Python | HTML |
| License | Apache-2.0 | MIT |
| Last activity | 4 days ago | today |
| Topics | memory, knowledge-graphs | memory, knowledge-graphs |
| Curated connections | 8 | 3 |
agent-memory — the curator's take
The pick when memory has to be queryable as a graph instead of a black box: entities resolve and dedupe, reasoning steps get explicit :TOUCHED audit edges to the entities they used, and you can adopt an existing Neo4j graph as long-term memory rather than re-ingesting. Multi-tenant scoping, buffered writes, consolidation primitives and an eval harness are already in the box, and the hosted NAMS tier lets you start with no database to run. Caveats: Neo4j Labs marks it Experimental and community-supported; extraction stacks spaCy/GLiNER/GLiREL plus an LLM pass, so ingest costs real time and tokens; and if you don't want a graph database in the stack at all, a Postgres- or file-backed layer is far less machinery.
linearmemory — the curator's take
Interesting for one design choice: memory is a chronological sequence of small observable events (reads, tool calls, decisions, errors, corrections) plus consolidated facts, decisions, procedures and outcomes — never the agent's raw reasoning transcript. Every graph edge carries direction, type, evidence, confidence and a human-readable explanation; humans browse the same store as a story, a relation map or a 3D graph. Postgres is authoritative, the graph projection is rebuildable, Docker Compose brings it up. NOT proven: one star, one author, no benchmark, no adopters yet. Watch it; don't bet on it.