Chroma is the open-source search and retrieval database for AI applications.
Vector, full-text, regex, and metadata search. Develop locally and scale to petabytes in the cloud backed by object storage. Serverless search and retrieval that is fast, cheap, and reliable.
5M+ monthly downloads
Apache 2.0
21k Github stars
Low latency search
Fast queries over billions of multi-tenant indexes.
Up to 10x cheaper
Built on object storage with automatic data tiering.
No engineering ops
Scales with your data and traffic. SOC 2 Type I.
What's new
still frame of interview
Beyond The Embedding: Vector Indexing
In this episode of Beyond The Embedding, Sanket Kedia talks through our implementation of SPANN and SPFresh.
Build and deploy
Install

Get up and running instantly.
Deploy

Run Chroma on AWS, GCP, Azure and more.
Scale

Chroma's distributed architecture is horizontally scalable, multi-tenant, and cloud native - powered by object storage.
Architecture
Cloud

Chroma's developer cloud is fully-managed, elastically scalable, with serverless billing. With the same API.
Cloud
FAQs
How can I get support? → Post a Github issue, or join our Discord.
Does Chroma have a fully-managed cloud version? → Yes, sign up.
What does Chroma cost? → Chroma is free and open-source under the Apache 2.0 License.
What does Chroma Cloud cost? → View Pricing
Are you hiring? → Yes

The Chroma newsletter

Tasteful updates, no more than once per week.

Get $5 in free credits on Chroma Cloud