Chroma

Health v2 · maintenance only

Adoption not part of the score

29471 stars · 2554 forks observed · 2026-10-10

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.97

Chroma is an open‑source data infrastructure that provides fast, scalable vector and full‑text search for AI applications. It can be self‑hosted or used as a managed cloud service.

Use cases

• store and query embeddings for semantic search
• perform hybrid vector‑and‑keyword search over large document collections
• filter search results by metadata tags or arrays
• build AI agents that retrieve relevant context from a knowledge base
• index code repositories for code‑search agents
• sync and ingest data from S3, GitHub or websites for searchable AI datasets

When to choose

• You need a high‑performance, low‑latency vector database with built‑in metadata filtering
• You want both dense and sparse (BM25) search capabilities in one system
• You prefer an open‑source solution that can run locally or in the cloud
• Your application requires seamless integration with Python, TypeScript, or Rust SDKs

When to avoid

• You require a fully managed relational database with complex transaction semantics
• Your workload is limited to simple key‑value storage without search needs
• You need on‑premise hardware acceleration that is not supported by Chroma’s current runtimes

Facets

service · maturity active

vector-database search-engine cli artificial-intelligence machine-learning windows cloud python rust hybrid-search full-text regex sparse-vectors serverless mcp metadata-arrays metadata-filtering retrieval-augmented-generation data-engineering linux macos docker nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="chroma-core/chroma")