Vector & retrieval

Chroma

Embeddable vector store that runs in-process, which makes it the quickest way to prototype retrieval.

Visit trychroma.com ↗

Pricing
Open source
Runs
Hosted or self-hosted
Languages
Python, TypeScript
Interface
Library, Server
Source
Open source

What Chroma is

Chroma runs in your process with no server to start, so a retrieval prototype is an import and a few lines. It persists to disk and can be run as a server later, which makes it a good first step whether or not it is the final one.

Best for

Prototyping retrieval, notebooks, and small applications where a service is overkill.

Consider something else if

In-process design is a poor fit for large corpora or many concurrent readers; plan the migration before you need it.

Chroma alternatives

The closest options in vector & retrieval, on the axes that actually separate them.

Chroma compared with 5 alternatives
ToolBest forPricingRuns
Chromaopen sourcePrototyping retrieval, notebooks, and small applications where a service is overkill.Open sourceHosted or self-hosted
pgvectoropen sourceAnyone already running Postgres with up to a few million vectors, which is a larger share of real applications than the category implies.Open sourceSelf-hosted
Qdrantopen sourceFilter-heavy retrieval — multi-tenant, permissioned, or time-scoped — where naive filtering degrades results.Open sourceHosted or self-hosted
PineconeTeams who want retrieval to be somebody else's operational problem and are content to pay for that.Usage-basedHosted
Weaviateopen sourceCorpora containing identifiers, product codes, or proper nouns, where pure vector search visibly misses.Open sourceHosted or self-hosted
turbopufferLarge corpora where only a fraction is queried regularly, and per-tenant indexes that are mostly idle.Usage-basedHosted

Choosing within vector & retrieval

Whether Postgres is already enough

Ask this first and take the answer seriously. At small and medium scale the extension removes a service, a sync problem, and a second consistency model, at very little cost in capability.

Metadata filtering

Real queries are almost never pure similarity — they are similarity within a tenant, a date range, or a permission scope. How well a store combines filters with vector search is the difference that shows up in production.

The full guide to vector & retrieval →

Questions

What is Chroma?

Chroma runs in your process with no server to start, so a retrieval prototype is an import and a few lines. It persists to disk and can be run as a server later, which makes it a good first step whether or not it is the final one. It is open source and hosted or self-hosted.

What are the alternatives to Chroma?

The closest alternatives are pgvector, Qdrant, Pinecone, Weaviate, turbopuffer. They sit in the same category — vector & retrieval — and differ mainly on hosting model, pricing shape, and how much they abstract away.

Is Chroma the right choice?

Prototyping retrieval, notebooks, and small applications where a service is overkill. The main caveat: In-process design is a poor fit for large corpora or many concurrent readers; plan the migration before you need it.