Chroma
Open-source embedding database for LLM applications. The default 'just install pip and start' vector store for prototypes, with first-party clients in Python and JS. SQLite-backed locally, distributed mode in cloud.
Overview
Open-source embedding database for LLM applications. The default 'just install pip and start' vector store for prototypes, with first-party clients in Python and JS. SQLite-backed locally, distributed mode in cloud.
Stack & relationships
How Chroma relates to other entries in the catalog — recommended pairings, alternatives, dependencies, and edges to avoid. Each edge carries a one-line operator note from our editorial team.
Works with
- Works withAnythingLLM
Drop-in alternative to LanceDB. Pick when you want a real DB with introspection tooling.
Alternatives
- Alternative toQdrant
Chroma is the simplest dev-experience vector store; Qdrant is the production upgrade once your collection sizes outgrow Chroma's single-node design.
- Competes withLanceDB
LanceDB stores vectors in Arrow files on disk — embeddable, zero-server. Chroma has a similar embeddable mode. LanceDB scales further before needing a real server.
- Alternative toLanceDB
Both are embedded-first; LanceDB scales further before needing a server, Chroma has the simpler dev experience. Pick LanceDB for workstation-tier RAG; Chroma for prototyping.
Pros
- Trivial local setup
- Strong Python ergonomics
- Active 17k★ community
Cons
- Performance trails Qdrant/Milvus at 100M+ vectors
- Schema flexibility costs query speed
Compatibility
| Operating systems | macOS Linux Windows |
| GPU backends | n/a |
| License | Open source · free (OSS) + managed cloud |
Get Chroma
Frequently asked
Is Chroma free?
What operating systems does Chroma support?
Which GPUs work with Chroma?
Reviewed by RunLocalAI Editorial. See our editorial policy for how we evaluate tools.