Hanzo Search
Hybrid search and RAG chat for your docs, apps, and APIs
Drop-in replacement for Algolia, Orama, and Typesense. Powered by Meilisearch + Qdrant.
Four search modes, one API
Full-text, vector, hybrid, and conversational search -- all from a single endpoint.
Full-Text Search
Meilisearch-powered instant search with typo tolerance, faceting, filtering, and sub-50ms response times out of the box.
Vector Search
Qdrant-powered semantic search with embeddings from 12+ providers. Find results by meaning, not just keywords.
Hybrid Search
Reciprocal Rank Fusion merges keyword and semantic results for the best of both worlds. One query, two engines.
RAG Chat
Ask questions and get AI answers grounded in your content with inline citations. Streaming responses, real sources.
How it works
Three steps from content to searchable, conversational knowledge.
Index your content
Push documents at build time or via the REST API. Meilisearch indexes text fields instantly. Qdrant stores vector embeddings from your chosen provider.
Search from any frontend
Use the React hook for instant UI, the REST API for custom integrations, or the MCP tool for agent workflows. One index, many surfaces.
Chat with your docs
Enable RAG chat and users can ask natural-language questions. Streaming AI answers cite your content with source links.
Works with any docs framework
Native support for Hanzo Docs, Fumadocs, Nextra, and Docusaurus. REST API for everything else.
Pricing
Pay for hosted search, vector, and AI. Self-host Meilisearch free forever.
Build
- 5 projects
- 10k docs per project
- 2,500 AI chat sessions
- Unlimited searches
- React hook + REST API
Scale
- 25 projects
- 100k docs per project
- 50,000 AI chat sessions
- Unlimited searches
- Priority support
Enterprise
- Unlimited projects
- Unlimited docs
- Unlimited AI chat sessions
- Unlimited searches
- Dedicated support + SLA
Meilisearch is open source. Self-host free forever. Pay only for our hosted API, vector search, and AI features.
25% of compute goes back to open source
Every deployment is SBOM-verified. Contributors to Meilisearch earn a share of compute revenue — transparent, on-chain, and customizable by the community.
Make your content searchable and conversational
Index once, search everywhere.
Full-text, vector, hybrid, and RAG -- all from one API.
Open source
Forked from Meilisearch (MIT). We track upstream and contribute fixes back where possible.