Quivr provides retrieval augmented generation for apps and supports multiple large language models and vector stores.
quivr
Quivr provides retrieval augmented generation for integrating generative AI into apps, with support for multiple models and vector stores.
About quivr
Quivr V2 is an open-source engine that turns continuous content streams into search and monitoring. It ingests content durably, makes text searchable within seconds, adds enrichments in the background, and allows following a topic over time.
It provides a Go API with REST v0, PostgreSQL for catalog and receipts, S3-compatible storage for canonical data, Temporal for orchestration, and Weaviate for lexical and vector search. Formats, models, and business rules are handled through plugins such as connectors, normalizers, enrichers, retrievers, and delivery channels. A single binary provides api, worker, and migrate commands, with local runtime via Docker Compose.
It suits developers evaluating infrastructure for search over changing content. The project states it is in evaluation stage with a v0 API that may change, and should not be run in production yet.
Key features
- Durable content ingestion with committed writes and idempotency keys
- Lexical and vector search using Weaviate with rehydrated hits
- Background enrichment including embeddings via local TEI service
- Plugin system for formats, models and business rules
- Topic monitoring with polling and SSE change feeds
- Single binary with api, worker and migrate commands
Best for: Developers evaluating a self-hosted engine for search and monitoring over continuous content streams.
Good for
- Durable storage in PostgreSQL and S3 with rebuildable indexes
- Generic core adaptable through plugins without forking
- Text searchable quickly before enrichments complete
- OpenAPI 3.1 contract and Docker Compose local runtime
Watch out for
- In evaluation stage with v0 API that may change
- Not for production use yet
- Local setup requires multiple dependencies and large downloads
quivr at a glance
- Website
- github.com/QuivrHQ/quivr
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
quivr alternatives
Tools and sites you could use instead, ranked by how closely they match.
EvoAgentX describes its project as an ecosystem of AI agents that can evolve over time.
Mem0 provides persistent memory infrastructure for AI agents and applications.
Open source
24 alternatives
The LangChain repository describes an agent engineering platform for building agent based software.
Open source
24 alternatives
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
Open source
24 alternatives
Upsonic provides a Python framework for creating autonomous AI agents.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
quivr FAQ
What is Quivr V2?
It is an open-source engine that ingests continuous content streams for search and monitoring, with durable storage and plugin-based enrichment.
Can Quivr be used in production?
No. The project states it is in evaluation stage and the v0 API may change, so it should not run in production yet.
How does Quivr handle search?
It uses Weaviate for lexical and vector search, rehydrates hits from canonical storage, and makes text searchable before embeddings arrive.
What is needed to run Quivr locally?
It requires Go 1.27.1, Docker with Compose v2, Python 3, Node.js 22+ and jq, with Docker Compose for dependencies.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.