#88th of 21 in RAG and knowledge
quivr
Go engine that ingests content streams for hybrid search and keyword alerts
- Stars
- 39.6k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Feb 2025
- Language
- Go
38,624 on 25 Mar 202639,589 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Quivr V2 is a Go service that durably ingests text and documents, indexes them in Weaviate for lexical, semantic and hybrid search, and runs saved queries as subscriptions that produce matches and signed webhooks. State lives in PostgreSQL and S3-compatible storage, with Temporal for orchestration and plugins for connectors and alert rules. The README marks it as evaluation stage with a v0 API that may change.
Who it is for: Engineers building search and alerts over content feeds
Strengths
- Idempotent writes and immutable Versions; search index can be rebuilt from PostgreSQL and S3
- Hybrid search rehydrates and re-authorizes every hit; outages return errors, not empty results
- Subscriptions with keyword, meaning and described alerts, plus signed webhook delivery
- Prometheus metrics, optional OpenTelemetry tracing, and documented worker autoscaling and upgrades
Weaknesses
- README says evaluation stage, API v0 may change, not for production
- Heavy stack: PostgreSQL, Temporal, Weaviate, S3 storage and a TEI embedding server
- No chat or LLM answer generation described; differs from the earlier Quivr assistant
- Described alerts send article text to TypeSafe; last release is February 2025
What it needs
- no GPU
- Docker + Compose
- Needs PostgreSQL 17, Temporal, Weaviate, S3-compatible storage (SeaweedFS locally), TEI (multilingual-e5-small), Docker Compose
- Models: multilingual-e5-small (384-dim, local TEI), custom embedding model server, hosted embedding API
- port 5183
Also in RAG and knowledge
See all 21| Rank | Project | Score |
|---|---|---|
| 1 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 78 out of 100 |
| 2 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 74 out of 100 |
| 3 | Open NotebookSelf-hosted NotebookLM alternative with podcasts and 20+ model providers | 74 out of 100 |
| #4 | LightRAGGraph-based RAG framework with a REST API server and web UI | 74 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 69 out of 100 |