---
source_url: "https://www.trychroma.com/products/chromadb?utm_source=openai"
title: ChromaDB - the open-source search infrastructure for AI
mirrored_at: 2026-08-14T01:01:19.872Z
host: www.trychroma.com
cited_in_42a: true
mirror_canonical: "https://index.42a.ai/www.trychroma.com/products/chromadb__q__utm_source_openai"
---

> **Original source:** https://www.trychroma.com/products/chromadb?utm_source=openai

## ChromaDB

The open-source search infrastructure for AI. Fast, serverless, and scalable. Supporting vector, full-text, regex, and metadata search. Built on object storage and trusted by millions of developers.

Trusted by teams at

![Capital One logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Fcapital-one.0k44g0j369u2l.png&w=3840&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![Weights & Biases logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Fwandb.0.b5gqy_nti~v.png&w=1080&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![UnitedHealthcare logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Fuhc.018kwqkts6v0k.png&w=1920&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![Live Nation logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Flivenation.0_z4nlwehzdov.webp&w=3840&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![Cisco logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Fcisco.03wzib~olpov..png&w=3840&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![Intel logo](https://www.trychroma.com/_next/image?url=%2F_next%2Fstatic%2Fmedia%2Fintel.0u8_jgk_8gm_k.png&w=3840&q=75&dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

![Sony logo](https://www.trychroma.com/_next/static/media/sony.04cfyfyym0ai5.svg?dpl=dpl_pSUeNSQiH7hkbFKHQ7yRHK5rJfMe)

## Open source at the core

Chroma is licensed under Apache 2.0. The same codebase powers both the open-source database and Chroma Cloud, so there is no vendor lock-in.

### Single-node

Run locally with pip, npm, or Docker. In-memory or persistent storage.

### Chroma Cloud

Fully managed, serverless, and scalable. No provisioning, no tuning. Get started in under 30 seconds.

### Bring your own cloud

Deploy in your own VPC with multi-region replication and point-in-time recovery. Full control over your infrastructure.

Many search methods, one platform

Chroma unifies dense vector search, sparse vector search, full-text search, regex matching, and metadata filtering in a single query interface. Combine them with hybrid search for the best retrieval quality.

◇

Sparse vector search

Lexical search (BM25, SPLADE)

◆

Vector search

Semantic similarity search

●

Full-text search

Trigram and regex search

◐

Metadata search

Filtering and faceted search

◊

Forking

Dataset versioning, A/B testing, and roll-outs

▣

CLI

Command-line tools for development

Fast search over billions of multi-tenant indexes

Chroma's indexes are built and optimized for object storage, offering unparalleled cost and performance. State-of-the-art vector, full-text, and regex search.

Latency

Query Latency

@384 dim at 100k vectors

Warm

Cold

p50

20ms

650ms

p90

27ms

1.2s

p99

57ms

1.5s

[Contact us](https://www.trychroma.com/talk-with-us)

to run a POC for your specific workload.  
Dedicated clusters can be scaled to your specific requirements.

Technical specs

Write throughput (per collection)30 MB/s (2000+ QPS)

Concurrent reads (per collection)10 (200+ QPS)

Collections per database1M

Records per collection5M

Recall90-100%

Zero-ops infra

Unlike legacy search systems, Chroma is a database you'll want to be on-call for.

✓Auto-scales with usage

✓No manual tuning

✓Serverless pricing

Chroma takes full advantage of object storage with automatic query-aware data tiering and caching.

✓Vectors are large: 1GB text → 15GB of vectors

✓Memory is expensive: $5/GB/mo

✓Object storage is not: $0.02/GB/mo

## Start searching with Chroma

## Hidden