Vearch provides distributed vector search capabilities for applications built around artificial intelligence.
Self-host
Chroma provides open-source data infrastructure for AI applications, with vector, full-text, regex, and metadata search.

About Self-host
Chroma provides data infrastructure for retrieval in AI applications. It stores documents, metadata, and embeddings, and supports dense, sparse, and hybrid vector search, full-text and regex search, metadata filtering, and retrieval across text, images, and audio.
It can run locally, be self-hosted, or be used as a managed cloud database, and is accessed through the Chroma SDK. It works with embedding models including OpenAI, Cohere, Hugging Face, and sentence-transformers, with examples for agentic search and code search using AST-aware chunking.
Key features
- Store documents with associated metadata and embeddings
- Dense, sparse, and hybrid similarity search
- Keyword and regex search without embeddings
- Filter search results by metadata conditions
- Index and search text, images, and audio
- Use models from OpenAI, Cohere, Hugging Face, and others
- Combines vector, full-text, regex, and metadata search in one system
- Works with multiple embedding providers and models
- Can run locally, be self-hosted, or use a managed cloud database
Self-host at a glance
- Website
- docs.trychroma.com
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Self-host alternatives
Tools and sites you could use instead, ranked by how closely they match.
RagTune helps inspect, debug, benchmark, and tune retrieval for retrieval augmented generation systems.
Lance provides an open lakehouse format for multimodal AI, with vector indexing and data versioning.
Popular in AI Data & Analytics
Well-known listings from the same topic.
Self-host FAQ
Can I run Chroma locally or use a hosted option?
Do I need to use a specific embedding model?
Can I search without embeddings?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.









