# Chroma review

> Chroma is open-source search infrastructure for AI, offering vector, full-text, regex, and metadata search through Python and JavaScript clients.

Devtoolwatch Board, the week of Oct 25–31, 2026. Canonical page: https://index.devtoolwatch.com/tools/chroma/

## TL;DR

Chroma is an open-source, Apache 2.0 search database for AI applications, with Python and JavaScript clients. It suits developers building retrieval and agent features who want a small API that handles embedding and indexing. It runs in-memory, in client-server mode, or as the hosted Chroma Cloud.

## Chroma at a glance

- **Category:** [RAG, data and memory](https://index.devtoolwatch.com/categories/rag-data-and-memory/)
- **Maintained by:** Chroma (organization, [@chroma-core](https://github.com/chroma-core) on GitHub)
- **License:** Apache 2.0
- **Language:** Rust, Python, TypeScript
- **Repository:** [github.com/chroma-core/chroma](https://github.com/chroma-core/chroma)
- **Website:** [www.trychroma.com](https://www.trychroma.com/)
- **npm package:** [chromadb](https://www.npmjs.com/package/chromadb) 3.5.0
- **PyPI package:** [chromadb](https://pypi.org/project/chromadb/) 1.5.9
- **Latest release:** [chromadb 3.5.0](https://www.npmjs.com/package/chromadb) on npm, Jun 30, 2026
- **First published:** Oct 5, 2022

## What Chroma does

- Chroma stores documents in collections and handles tokenization, embedding, and indexing automatically, or accepts your own embeddings.
- Chroma queries collections for the most similar results to a query text and can also get documents by id.
- Chroma filters results on metadata fields and on document contents, such as a $contains string match.
- Chroma supports sparse vector search for lexical ranking with BM25 and SPLADE.
- Chroma offers full-text search with trigram and regex matching, plus faceted metadata search.
- Chroma supports forking for dataset versioning, A/B testing, and roll-outs.
- Chroma includes command-line tools for development.

### How it works

Chroma installs as the chromadb package for Python or npm. You can run it in-memory for prototyping, add persistence, or start a server with chroma run for client-server mode. The hosted Chroma Cloud provides serverless search built on object storage such as S3 or GCS, with memory and SSD caching for hot and warm data.

## How to install Chroma

**With pip**

```
pip install chromadb
```

**With npm**

```
npm install chromadb
```

**Run in client-server mode**

```
chroma run --path /chroma_db_path
```

### Requirements

- Python 3.9 or later for the Python package.
- Node.js 20 or later for the JavaScript package.
- A Chroma Cloud account for the hosted service.

### First steps

1. Create a client with chromadb.Client() to run Chroma in-memory for prototyping.
2. Create a collection with client.create_collection and a name such as "all-my-documents".
3. Add documents with collection.add, passing documents, optional metadatas, and a unique id for each document.
4. Search with collection.query using query_texts and n_results, optionally adding where or where_document filters.

## Who Chroma is for

- Developers prototyping retrieval for AI apps who want a small API with automatic embedding.
- Teams that need vector, full-text, regex, and metadata search in one system.
- Python and TypeScript developers building search features for AI agents.
- Teams that want a hosted, serverless option instead of running search infrastructure themselves.

### Limitations

- Chroma describes itself as a rapidly developing project, so APIs may change; a row-based API is listed as coming soon.
- Chroma Cloud lists per-collection limits, including 5M records per collection and 1M collections per database.
- Chroma Cloud cold queries are slower than warm ones in the homepage's published latency figures.

## Usage data (the week of Oct 25–31, 2026)

- Board rank: #248 overall, #28 in RAG, data and memory, momentum score 38
- Downloads that week: 2.3M (+10% vs 4-week average)
- New GitHub stars per week (last 12 weeks): Aug 9: 84; Aug 16: 80; Aug 23: 62; Aug 30: 64; Sep 6: 58; Sep 13: 57; Sep 20: 66; Sep 27: 52; Oct 4: 58; Oct 11: 60; Oct 18: 62; Oct 25: 51

## Chroma alternatives

| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | [XERJ](https://index.devtoolwatch.com/tools/xerj-org-xerj/) | 17.9k | – |
| #2 | [Memvid](https://index.devtoolwatch.com/tools/memvid-memvid/) | 17.3k | – |
| #3 | [LEANN](https://index.devtoolwatch.com/tools/startrail-org-leann/) | 13.7k | – |
| #4 | [Graphify](https://index.devtoolwatch.com/tools/graphify-labs-graphify/) | 140k | 480.7k |
| #5 | [MarkItDown](https://index.devtoolwatch.com/tools/markitdown/) | 193.2k | 4.7M |
| #6 | [Firecrawl](https://index.devtoolwatch.com/tools/firecrawl/) | 197.4k | 2.9M |

## Chroma FAQ

### Is Chroma free and open source?

Yes. Chroma's source code is on GitHub (chroma-core/chroma) under the Apache 2.0 license, so you can use it for free. Its website also links to a pricing page (https://www.trychroma.com/pricing) for any paid plans.

### How do I install Chroma?

Run `pip install chromadb`. It needs Node.js >=20. The install section above has the other options from the project's README.

### Is Chroma still maintained?

Yes. The chroma-core/chroma repository was last updated on Oct 22, 2026, and the latest release, chromadb 3.5.0 on npm, came out on Jun 30, 2026.

### How popular is Chroma?

Chroma has 29.6k GitHub stars as of Nov 1, 2026. It gained 51 new stars in the week of Oct 25–31, 2026, against a 12-week average of 63 a week. Its main package had about 2.3M downloads that week, +10% against its own 4-week average. That made it #28 among RAG, data and memory tools on the Devtoolwatch Board.

### Chroma vs Qdrant: how do they compare?

Chroma and Qdrant are both tracked by Devtoolwatch as RAG, data and memory tools. Chroma has 29.6k GitHub stars and Qdrant has 35.4k. In the week of Oct 25–31, 2026, Chroma's main package had 2.3M downloads and Qdrant's had 4.5M. Qdrant is an open-source vector similarity search engine and vector database written in Rust, with filtering on JSON payloads. [Qdrant review](https://index.devtoolwatch.com/tools/qdrant/)

### Chroma vs pgvector: how do they compare?

Chroma and pgvector are both tracked by Devtoolwatch as RAG, data and memory tools. Chroma has 29.6k GitHub stars and pgvector has 23.5k. In the week of Oct 25–31, 2026, Chroma's main package had 2.3M downloads and pgvector's had 9.4M. pgvector is an open-source Postgres extension for exact and approximate vector similarity search, storing vectors alongside the rest of your data. [pgvector review](https://index.devtoolwatch.com/tools/pgvector/)

### What are the best alternatives to Chroma?

Other RAG, data and memory tools on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: XERJ (#1), Memvid (#2), LEANN (#3), Graphify (#4), MarkItDown (#5). The alternatives table above has their numbers.

### Is ChromaDB free?

Chroma is open source under the Apache 2.0 license. The hosted Chroma Cloud is a separate service, and the README says new users get $5 of free credits.

### Can Chroma create embeddings for me?

Chroma handles tokenization, embedding, and indexing automatically when you add documents. You can also skip that step and supply your own embeddings.

### Does Chroma support keyword or full-text search, not just vectors?

Chroma supports sparse vector search with BM25 and SPLADE, full-text search with trigram and regex matching, and metadata filtering alongside vector similarity search.

### How often does Chroma release new versions?

Chroma releases new tagged versions of its pypi and npm packages on Mondays. Hotfixes ship at any time during the week.

### Can I run Chroma as a server?

Chroma runs in client-server mode with the chroma run command and a data path. It can also run in-memory inside your application for prototyping.

## Sources

1. [chroma-core/chroma on GitHub](https://github.com/chroma-core/chroma)
2. [Chroma README](https://github.com/chroma-core/chroma/blob/main/README.md)
3. [chromadb on npm](https://www.npmjs.com/package/chromadb)
4. [chromadb on PyPI](https://pypi.org/project/chromadb/)
5. [Chroma website](https://www.trychroma.com/)
6. [Release latest (Apr 1, 2025)](https://github.com/chroma-core/chroma/releases/tag/latest)
7. [Release 1.5.9 (May 5, 2026)](https://github.com/chroma-core/chroma/releases/tag/1.5.9)
8. [Release cli-1.4.4 (May 5, 2026)](https://github.com/chroma-core/chroma/releases/tag/cli-1.4.4)
9. [Hacker News: Context Rot: How increasing input tokens impacts LLM performance](https://news.ycombinator.com/item?id=44564248)
10. [Hacker News: Show HN: Chroma Cloud – serverless search database for AI](https://news.ycombinator.com/item?id=44944241)
11. [Hacker News: Chroma Context-1: Training a Self-Editing Search Agent](https://news.ycombinator.com/item?id=47534564)
12. [Devtoolwatch Board, the week of Oct 25–31, 2026](https://index.devtoolwatch.com/)