AI Potluck
Infrastructure / Storage & Retrieval

Chroma

Chroma

Chroma is a retrieval database for AI applications, storing embeddings with their documents and metadata behind a four-function API. It runs embedded in a Python or JavaScript process, as a self-hosted server, or on the vendor's hosted service, and the core is implemented in Rust with a Kubernetes deployment path in the repository. Hybrid and full-text search sit beside vector search.

Verified 2026-08-18 via the GitHub API and the LICENSE body.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI)
source
public
core-gated
ungated

Apache-2.0 license body confirmed. The repository is public and unarchived and builds the whole product, and the README describes no paid tier, enterprise edition or license-gated build beside it, so source is public and the core ungated. Chroma Cloud is a hosted service sold beside the Apache-2.0 core rather than a piece withheld from it: the repository carries the Rust engine, the clients and the Kubernetes deployment manifests, which is the langchain shape rather than the litellm one.

Adoption

5 high confidence
5.0

13,053,849 PyPI downloads of `chromadb` in the trailing 30 days, which lands in the >10M band of the software usage scale, level 5.

Capability

4 medium confidence
4.0

Banded on the category feature matrix as complete retrieval system, distributed or cluster-capable. Placed one band below the vespa anchor, on a matrix that bands on how much of the persist-index-retrieve path a product provides itself, at what scale and over how many retrieval modes.

Verified 2026-08-18