HTTP 200 verified twice
Finding your next stop…
Loading the latest directory information.
Loading the latest directory information.
Start here for the decision-making essentials: what Chroma does, who it is for, how it is accessed, and the first-party sources behind this profile.
$0.0075 per TiB queried and $0.09 per GiB returned for reads
Read-only public captures of Chroma’s homepage. Screenshots are dated, never live embeds, and open full-screen.
Chroma is an open-source (Apache 2.0) data infrastructure for AI that stores embeddings and supports dense, sparse, hybrid, keyword, and regex search across text, images, and audio. It runs as self-hosted single-node, distributed, or managed Chroma Cloud, with AWS CloudFormation deployment, a CLI, and Mem0 integration.
Short answers to the questions buyers and builders commonly ask about Chroma. Each answer cites the shared ledger below, where every source is listed once.
Stores embeddings with metadata, searches with dense and sparse vectors, filters by metada · Supports dense, sparse, and hybrid search as well as keyword and regex search without embe · Instant copy-on-write collection forking is offered in Chroma Cloud, letting forks share d · CLI provides DB management, collection copying and browsing operations
store embeddings with metadata, search with dense and sparse vectors, filter by metadata, and retrieve across text, images, and more
Build agents that iteratively search and refine results for complex queries · Index codebases to power coding agents using AST-aware chunking · Forking supports data versioning/checkpointing and git-like workflows (e.g., indexing a br · Sample AI applications powered by Chroma for learning retrieval and building AI apps
Build agents that iteratively search and refine results for complex queries.
Collection forking is not supported on single-node Chroma storage engine; available in Chr · Vacuuming blocks all reads and writes to the database while running · CLI collection browser initially loads only 100 records, with more loaded on scroll · Local Chroma may temporarily lack some features or behaviors available in the distributed
Forking is available in Chroma Cloud only. The storage engine on single-node Chroma does not support forking.
$0.0075 per TiB queried and $0.09 per GiB returned for reads · $0.33 per GiB per month for storage (prorated by the hour) · Fork call | $0.03 per fork call | incremental blocks written after the fork (copy-on-write
$0.0075 per TiB queried - $0.09 per GiB returned
Chroma provides a fork API accessible from Python or JavaScript SDKs · API key authentication available for headless environments via Chroma Cloud dashboard · Chroma Cloud can be configured via the environment variables CHROMA_API_KEY, CHROMA_TENANT
SDKs: Use the fork API from Python or JavaScript.
Works with any embedding model including OpenAI, Cohere, Hugging Face, and sentence-transf · Chroma integrates with Mem0 as a vector store provider, configured via vector_store.provid · CLI profile authentication uses an API key and tenant ID for Chroma Cloud, stored in .chro
Use any embedding model. OpenAI, Cohere, Hugging Face, sentence-transformers, and more.
This profile connects the jobs Chroma is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
HTTP 200 verified twice
Introduction - Chroma Docs
Open-source AI data infrastructure licensed under Apache 2.0 · Stores embeddings with metadata, supports dense, sparse, and hybrid search · Supports keyword and regex search without embeddings
Stores embeddings with metadata, searches with dense and sparse vectors, filters by metadata, and retrieves across text, images, and more
Supports dense, sparse, and hybrid search as well as keyword and regex search without embeddings
Works with any embedding model including OpenAI, Cohere, Hugging Face, and sentence-transformers
Can be deployed as a self-hosted database or a managed zero-ops Chroma Cloud database
Build agents that iteratively search and refine results for complex queries
Index codebases to power coding agents using AST-aware chunking
Indexes and searches images, audio, and other modalities alongside text
Yes - Chroma is open-source data infrastructure for AI
$0.0075 per TiB queried and $0.09 per GiB returned for reads
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
This profile is being checked for dated releases and material product changes. Nothing appears here until the exact date and event can be verified from a recorded source.
Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.
These tools share a workflow, capability or audience with Chroma. They may complement it rather than replace it, and are not presented as integrations or endorsements.
$0.33 per GiB per month for storage (prorated by the hour)
Chroma integrates with Mem0 as a vector store provider, configured via vector_store.provider = "chroma" with collection_name and path settings
Instant copy-on-write collection forking is offered in Chroma Cloud, letting forks share data blocks with the source collection
Collection forking is not supported on single-node Chroma storage engine; available in Chroma Cloud only
Fork call | $0.03 per fork call | incremental blocks written after the fork (copy-on-write); unchanged data remains shared
Forking supports data versioning/checkpointing and git-like workflows (e.g., indexing a branch from a divergence point and applying a diff)
Chroma provides a fork API accessible from Python or JavaScript SDKs
Chroma can be run as a local server using the `chroma run` CLI command, with data persisted to a configurable directory
Local Chroma server defaults to host `localhost` and port `8000`, configurable via CLI arguments or a config_path configuration file
Forked collections belong to the same database as the source collection in Chroma Cloud
CLI provides DB management, collection copying and browsing operations
Inspect Chroma collections with an in-terminal UI
Browse collections on Chroma Cloud or a local Chroma server via CLI
Stores collections of records with IDs, documents, and metadata
Supports .get() queries on collections via CLI query editor
Vacuum operation shrinks and optimizes the Chroma database
Hosted Chroma Cloud database service available
Local Chroma server runs by default at http://localhost:8000
Available via Python and JavaScript packages (chromadb)
API key authentication available for headless environments via Chroma Cloud dashboard
Vacuuming blocks all reads and writes to the database while running
CLI collection browser initially loads only 100 records, with more loaded on scroll
Open-source data infrastructure for AI
Apache 2.0
Two deployment modes: distributed Chroma and single-node local Chroma
Chroma Cloud runs the same open-source distributed system as the self-hosted database
True - open-source project accepting contributions via GitHub pull requests
Local Chroma may temporarily lack some features or behaviors available in the distributed system; restoring 100% feature and API parity is an active goal
