omnigraph vs pgGraph
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. — versus — PostgreSQL extension adding graph search, traversal and shortest-path over your existing tables — a derived graph index queried from plain SQL, no separate graph DB or query language. Rust.
Graph context for agents, opposite deployment bets: omnigraph is a standalone lakehouse runtime on Lance/S3; pgGraph lives inside the Postgres you already run.
| omnigraph | pgGraph | |
|---|---|---|
| Stars | 1.0k | 898 |
| Forks | 206 | 76 |
| Language | Rust | Rust |
| License | MIT | NOASSERTION |
| Last activity | 2 days ago | 3 days ago |
| Topics | memory, knowledge-graphs | knowledge-graphs, rag |
| Curated connections | 7 | 2 |
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.
pgGraph — the curator's take
The zero-migration bet: your tables stay the source of truth and the graph is a derived index, which makes it the cheapest possible on-ramp to GraphRAG over data already in Postgres. When NOT: the license is NOASSERTION with a managed-service funnel (polygres.com) — read the terms before production; graph-native workloads at scale still favor a dedicated store; ★898 and v1.0-young.