Tools · SPBoucher
Menu

Chroma

by Chroma · Database · also known as ChromaDB

Open-source embedding database with a minimal Python and JavaScript API, usable in-process, as a server or through Chroma Cloud

Apache-2.0 licenseOpen sourceUsage-basedLocalSelf-hostedCloudSelf-hostable
Visit official site Compare

Link verified Nov 2, 2026

Overview

Chroma is an open-source embedding database released under Apache 2.0 by the company of the same name. Its API is deliberately small: create a collection, add documents with optional metadata and embeddings, and query by text or vector with metadata and document filters. A pluggable embedding-function interface calls OpenAI, Cohere, Hugging Face, Ollama or local sentence-transformers so that users can hand Chroma raw text. The core has been rewritten in Rust, and the same client code works against an in-process instance in a notebook, a standalone server, or the hosted Chroma Cloud service.

Chroma is the default vector store in many LangChain and LlamaIndex tutorials and is well suited to prototypes, local RAG applications and evaluation experiments. Collections persist to local disk; full-text and regex search complement vector queries. Compared with Qdrant, Milvus or Weaviate, the self-hosted server has fewer options for distributed scaling and operational tuning, so large or multi-tenant production deployments are the domain of Chroma Cloud or a different engine.

Capabilities

  • Collections with vector, metadata and full-text filtering
  • Pluggable embedding functions for hosted and local models
  • In-process (embedded) or client-server operation
  • Python and JavaScript/TypeScript clients
  • Persistent local storage
  • Managed Chroma Cloud with usage-based pricing

Typical workflows

  1. Local RAG prototype inside a Jupyter notebook
  2. Vector store for a LangChain or LlamaIndex application
  3. Evaluation of embedding models on a document corpus

Strengths

  • Very small API surface
  • Runs embedded with no server for development
  • Apache 2.0 license

Limitations

  • Self-hosted server lacks distributed scaling
  • Fewer index and quantization options than specialized engines
  • Operational tooling is lighter than mature databases

Prerequisites

  • Python or Node.js, or a Chroma Cloud account

Who it is for

  • Developers prototyping RAG applications
  • Researchers running retrieval experiments

Alternatives & comparison

  • Milvus

    Open-source vector database from Zilliz with Lite, Standalone and Distributed deployments, many index types and GPU acceleration

    Open sourceOpen source
  • pgvector

    PostgreSQL extension adding vector types, distance operators and HNSW/IVFFlat indexes for similarity search inside the database

    Open sourceOpen source
  • Pinecone

    Fully managed, proprietary vector database service with serverless indexes, namespaces, metadata filtering and integrated embedding and reranking

    ProprietaryFreemium
  • Qdrant

    Open-source vector search engine written in Rust with filterable HNSW indexes, sparse and multi-vector support, REST/gRPC APIs and a managed cloud

    Open sourceOpen source
  • Weaviate

    Open-source vector database in Go with pluggable vectorizer modules, hybrid BM25 and vector search, multi-tenancy and a managed cloud

    MixedOpen source
Compare Chroma with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

  • License
    Chroma LICENSE (Apache 2.0)

    https://github.com/chroma-core/chroma/blob/main/LICENSE

    Supports: license_spdx, source_model

    checked Nov 1, 2026
  • Official documentation
    Chroma Docs

    https://docs.trychroma.com/

    Supports: capabilities, interfaces, languages

    checked Nov 1, 2026
  • Official site
    Chroma

    https://www.trychroma.com/

    Supports: name, summary

    checked Nov 1, 2026
  • Pricing page
    Chroma Cloud pricing

    https://www.trychroma.com/pricing

    Supports: pricing_model

    checked Nov 1, 2026
  • Repository
    chroma-core/chroma

    https://github.com/chroma-core/chroma

    Supports: repo_url

    checked Nov 1, 2026
Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

Elasticsearch

Elastic N.V. · Vector databases

In-depth entry

Distributed search and analytics engine on Apache Lucene with full-text, aggregations, vector search and ES|QL; triple-licensed AGPL, SSPL and Elastic License

AGPL-3.0-only OR SSPL-1.0 OR Elastic-2.0Open sourceFreeSelf-hostedNov 2, 2026

Meilisearch

Meili SAS · Vector databases

Rust search engine for application search-as-you-type with typo tolerance, faceting and hybrid semantic search; MIT core plus BSL enterprise parts

MIT AND BUSL-1.1Open sourceFreeSelf-hostedNov 2, 2026

OpenSearch

OpenSearch Software Foundation (Linux Foundation) · Vector databases

Apache-2.0 search and analytics suite forked from Elasticsearch and Kibana, governed by the OpenSearch Software Foundation

Apache-2.0Open sourceFreeSelf-hostedBroken

Typesense

Typesense, Inc. · Vector databases

GPL-licensed in-memory search engine in C++ offering typo-tolerant instant search, faceting, vector and hybrid search, with Typesense Cloud hosting

GPL-3.0Open sourceFreeSelf-hostedNov 2, 2026