agent-memory vs omnigraph
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 — Lakehouse graph database for agent context — graph, vector and full-text retrieval fused in one runtime on branchable Lance/S3 storage; agent fleets write on isolated branches and merge Git-style.
Both sell graph-native agent context. OmniGraph is a lakehouse engine with branchable Lance storage for agent fleets; Neo4j Agent Memory is an opinionated short-term/long-term/reasoning memory API on a database most teams already know.
| agent-memory | omnigraph | |
|---|---|---|
| Stars | 478 | 1.1k |
| Forks | 94 | 249 |
| Language | Python | Rust |
| License | Apache-2.0 | MIT |
| Last activity | 3 days ago | 4 days ago |
| Topics | memory, knowledge-graphs | memory, knowledge-graphs |
| Curated connections | 4 | 9 |
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.
omnigraph — the curator's take
Reach for it when many agents must share one evolving knowledge store and you need blame, rollback and review on their writes — branch-per-agent with merge gates is the feature nothing else in this space has; also strong when retrieval genuinely needs graph + vector + full-text fused, not a vector store with metadata filters. NOT a drop-in vector DB: you take on a server, cluster.yaml, schemas and Cedar policy — for plain RAG recall, Chroma is answering queries before you've finished omnigraph's docs. Young project on a credible Rust/Lance foundation; expect sharp edges and a moving API.