Managed vector database built on Milvus with hybrid search, a free tier, AWS, Google Cloud and Azure, plus bring-your-own-cloud.

Chroma overview and key facts (October 2026)
Open-source embedding database with a four-function API, usable locally or as managed Chroma Cloud.
What is Chroma?
Chroma is an open-source embedding database for building retrieval into AI applications. Developers add documents, and Chroma embeds, indexes and searches them through a small API, locally or in the managed Chroma Cloud.
Chroma runs in memory for prototypes, with local persistence, in client-server mode or as the distributed Chroma Cloud. The core API has four functions to create collections, add documents, query and get records. The repository is licensed under Apache 2.0, has more than 29,000 GitHub stars and was last updated on September 26, 2026. Chroma Cloud runs multi-tenant in AWS us-east-1 and GCP europe-west1, with single-tenant and BYOC options on Enterprise.
Chroma AI features and use cases
- Embeds documents automaticallyWhen documents are added, Chroma handles tokenization, embedding and indexing, or accepts embeddings you supply. Developers build a searchable knowledge base in a few lines of code.
- Retrieves passages for RAGQueries return the most similar documents, filtered by metadata or content. Chat assistants receive relevant passages from internal sources to answer questions.
- Scales search in the cloudChroma Cloud provides serverless vector, hybrid and full-text search, with each database kept in the chosen region. Teams move from a local prototype to production without running servers.
What sets Chroma apart
- Small API of four functions and an in-memory mode for quick prototypes.
- Cloud region choice between the US and the EU (GCP europe-west1).
- Apache 2.0 license with weekly releases of the Python and JavaScript packages.
Where Chroma is strongest
Chroma Inc. is based in San Francisco; the cloud runs in AWS us-east-1 and GCP europe-west1.
Questions to ask before you buy Chroma
If you self-host, plan persistence, backups and upgrades yourself, since the project releases new versions weekly. For Chroma Cloud, choose the EU region when data must stay in Europe and check the usage-based costs for writes, storage and queries. SOC 2 is listed for the Team plan, and single-tenant or BYOC clusters require Enterprise. Chroma publishes a data processing addendum and a sub-processor list for its cloud service.
Using Chroma in the EU: GDPR and AI Act
- Data locationMultiple regions, EU region available (according to the vendor). Hosting regions: United States, EU.
- Data processing agreementPublic, read it here (opens in a new tab). Subprocessor list (opens in a new tab).
- EU AI ActCheck whether the AI prepares decisions about people. If not, the high-risk rules usually do not apply. The high-risk obligations apply from December 2, 2027 (Digital Omnibus).
Chroma reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about Chroma
Is Chroma free?
The open-source database is free under Apache 2.0. Chroma Cloud has a $0 Starter plan billed by usage after $5 in free credits.
Where does Chroma Cloud run?
The multi-tenant service runs in AWS us-east-1 and GCP europe-west1, and each database stays in the region you choose.
Can I bring my own embeddings?
Yes. Chroma can create embeddings automatically, and you can also add your own embeddings.
Chroma update historyno updates yet
No changes recorded for Chroma yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to Chroma
Tools in the same category (Embedding stores) with the most overlapping markets.
Embedded open-source database for multimodal AI data on the Lance columnar format, with vector, full-text and SQL search.
Serverless search engine on object storage for vector, full-text and hybrid search, with regions in North America, Europe and Asia Pacific.
Open-source vector database from Amsterdam with hosted embedding models and a Query Agent for natural-language queries.



