omnigraph vs xerj
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 — One Rust binary for agent search: BM25, vector and hybrid search over code, docs, logs and PDFs, an Elasticsearch-compatible API, MCP, and Query-1, which answers by running programs over facts.
Both fuse full-text, vector and structured retrieval in one runtime for agent context.
| omnigraph | xerj | |
|---|---|---|
| Stars | 1.9k | 19k |
| Forks | 262 | 1.4k |
| Language | Rust | Rust |
| License | MIT | Apache-2.0 |
| Last activity | yesterday | today |
| Topics | memory, knowledge-graphs | rag, storage |
| Curated connections | 13 | 3 |
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.
xerj — the curator's take
Use it when you want a single self-hosted search engine for agents across code, docs and data instead of Elasticsearch plus a vector DB, or when wrong answers are costly and you want UNKNOWN or CONFLICT instead of guesses. Skip it if you just need grep-replacement for one repo, since it is a whole engine to operate. The headline benchmark numbers come from the project itself.