Report card

Do AI agents pick Chroma?

How often agents choose Chroma when a developer needs vector database — measured across Claude, GPT, Gemini.

Chroma

#3 of 5 vector db
1%Pick Rate
95% CI 0%3%

When developers ask an AI agent for vector db, Chroma is picked 1% of the time — ranking #3 of 5 measured across Claude, GPT, Gemini.

Picked 1% Named, not picked 23% Never surfaced 76%

Beaten by Pinecone (30%), pgvector (13%).

Awareness

0 docs in FineWeb (10BT sample) · 77 URLs in Common Crawl

In the raw web crawl, but thin in the filtered corpus models actually train on — an awareness gap at the source.

AdoptionDid the pick convert to installs? Public Adoption = npm downloads of your packages. The proof half of the funnel.

788K installs / month flat

Installs are roughly flat month over month.

Get the full report

The per-model and per-surface breakdown for Chroma — where it wins, where it loses, and to whom — plus an alert when the Pick Rate moves.

About Chroma

An open-source vector database for building AI applications.

Chroma is an open-source data infrastructure layer that stores and queries embeddings, documents, and metadata, enabling LLMs to access external knowledge, facts, and skills. It supports both self-hosted deployments (via the Chroma CLI) and a hosted serverless option called Chroma Cloud with full-text and vector search. It is aimed at developers building LLM-powered applications that need to retrieve and manage contextual data.

Where to start

You can run a local Chroma server with the Chroma CLI using `chroma run`, then connect to it from your application using the JavaScript/TypeScript client or the native Python library. Official documentation and a Colab example are available to walk through initial setup.

Install

Links and summary verified from public sources.

The rest of the Vector Database ranking

← Full Vector Database leaderboard · How this is measured