Head to head
hubmesh vs haiku.rag
Same numbers we show everywhere else, lined up. Ratings come from users, the grade comes from our scanner, adoption comes from public registries.
No reviews yet
Deterministic multi-hop graph retrieval for RAG. Zero LLM calls in the query path.
Full listing
No reviews yet
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
Full listingThe short version
Neither has been reviewed yet, so the comparison rests on the scan and the public usage numbers. Both score close on the safety scan (92 and 92 out of 100). haiku.rag has noticeably more public adoption.
| hubmesh | haiku.rag | |
|---|---|---|
| User rating | No reviews yet | No reviews yet |
| Safety grade | A92/100 | A92/100 |
| Adoption | Growing | Established |
| GitHub stars | 2 | 609 |
| Downloads / week | 130 | – |
| Runs where | Your machine (local) | Your machine (local) |
| Gateway-ready | No | No |
| Tools | 8 | — |
| Write actions | — | — |
| Price per call | Free | Free |
| Licence | MIT | MIT |
| Last release | 2026-09-19 | 2026-09-18 |
| Category | AI and agents | AI and agents |