Quivr

What is Quivr?

Quivr is a self-hosted engine, written in Go, for teams that need to take in a steady stream of documents, feeds and messages and then search or watch it. Applications call a versioned HTTP API to add content, run searches and set alerts. Search works by keyword, by meaning or by both at once, and the engine lets you choose a default profile or a deeper one that re-ranks within a time and cost budget. Alerts can match on keywords or on meaning, and collection guides cover RSS and Atom feeds, Microsoft 365 mail, X lists and archive imports. Formats, embedding models and ranking rules live in separate plugin services, so operators swap them without rebuilding the core. One binary runs the API, a worker and a migrate command, and a Compose file packages a single-machine setup. There is no price: you run it yourself. The docs say it is at an evaluation stage with a v0 API that may change, and advise against production use for now.

Use cases

• Ingest continuous content streams
• Search records by keyword and meaning
• Set keyword or meaning alerts
• Collect RSS feeds and mail
• Import archives of documents
• Connect an AI agent to a content store
• Compare embedding models for search

Who it's for

• Backend developers
• Platform engineers
• Search engineers
• AI application builders

Why use Quivr

• Content from feeds, mail and archives lands in one searchable store behind a single API, so applications do not each build their own pipeline.
• Hybrid search lets you mix keyword matching and meaning-based matching, and the weights are tunable per deployment.
• Alerts that match by meaning catch relevant items that exact keywords would miss.
• Plugin services keep formats, embedding models and ranking rules replaceable without changing the core engine.
• Running it yourself means your data stays on infrastructure you control.

Quivr features

• HTTP API for ingesting records and running searches
• Hybrid keyword and vector search
• Search profiles named default and deep
• Optional paid re-ranking with Jev
• Keyword alerts and meaning alerts
• Connectors for RSS and Atom, Microsoft 365 mail and X lists
• Archive import for large loads
• Plugin services for connectors, ingestion, retrieval and alert rules
• Vector space backfill and embedding model switching
• Single binary with api, worker and migrate commands

Quivr integrations

• Microsoft 365
• X lists
• Weaviate
• Jev

How to get started with Quivr

1. Start a local stack with make dev or the one-machine Compose file, after running quivr migrate.
2. Keep the quivr api and quivr worker processes running with a JSON configuration file.
3. Add content through the API, a connector for a source such as an RSS feed, or an archive import.
4. Search with the default or deep profile, choosing keyword, meaning or hybrid mode.
5. Create keyword or meaning alerts and, if needed, add plugins for re-ranking or new vector models.

Quivr limitations

• The docs call Quivr evaluation stage and recommend against production use
• The HTTP API is v0 and may change
• You operate the deployment yourself, including plugins, configuration and restarts
• Jev re-ranking is an optional paid model from TypeSafe

Quivr pricing

Quivr is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Quivr alternatives

The main Quivr alternatives listed on Debuly are Weaviate, Haystack, Azure AI Search, Baseplate, Singlebase and Agentset. The table compares pricing and platforms; order is A–Z.

1. 

   Agentset

   RAG-as-a-service for developers: ingest documents, run agentic search and build chat with citations through an API and SDKs.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Agentset (official site)
2. 

   Azure AI Search

   Managed Microsoft Azure search service for full-text, vector and hybrid retrieval, with agentic retrieval and a free tier for AI apps and RAG.

   Developer platformsResearch and searchAutomation and agents
   FreemiumVisit Azure AI Search (official site)
3. Ba

   Baseplate

   Backend for LLM apps: a hybrid database for data and embeddings, search, an app builder and API endpoints

   Developer platformsAutomation and agents
   FreemiumVisit Baseplate (official site)
4. 

   Haystack

   Open-source Python framework from deepset for building RAG pipelines, AI agents and multimodal apps from modular components.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Haystack (official site)
5. 

   Singlebase

   Backend platform for apps and AI agents with a JSON document database, vector search, identity, storage and scoped agent keys.

   Developer platformsAutomation and agentsResearch and search
   PaidVisit Singlebase (official site)
6. 

   Weaviate

   Open-source vector database with hybrid search and a managed Weaviate Cloud for semantic search, RAG and recommendations.

   Developer platformsResearch and search
   FreemiumVisit Weaviate (official site)

Quivr FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from mintlify.s3.us-west-1.amazonaws.com · fetched 24 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.