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.
Pricing2 plans
Starterper month
$0/month + usage
10 databases, 10 team members, Community Slack
Teamper month
$250/month + usage
100 databases, 30 team members, Slack support, SOC II, Volume-based discounts
Platforms
Chroma Cloud
API accessNot public
FoundedNot disclosed by source
AvailabilityWeb / remote
LicenseApache 2.0
Best suited to
Source-backed fit
Teams building AI agents requiring fast, scalable search infrastructure Organizations needing SOC 2 Type II compliant cloud search with SSO and CMEK Developers seeking open-source vector, full-text, regex, and metadata search
AI infrastructure · Tool
Chroma
Decision-ready
Chroma is open-source Apache 2.0 search infrastructure for AI, offering serverless, scalable vector, full-text, regex, and metadata search on object storage. Available as Chroma Cloud with SOC 2 Type II, CMEK, BYOC, and multi-cloud replication.
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.
01What does Chroma say it can do?
Vector, full-text, regex, and metadata search · Serverless, scalable search infrastructure · Hybrid search combining native SPLADE (sparse vector keyword) support with dense vectors f · Single database designed to hold hundreds of thousands of collections, enabling one-collec
Fast, serverless, and scalable infrastructure supporting vector, full-text, regex, and metadata search.
Powers agent and human search for AI-driven developer documentation platforms (e.g., Mintl · GroupBy enables diversification, deduplication by metadata keys like document_id, and mult · Indexing product docs, change logs, support pages, blogs, or any other web source used by
Chroma Cloud powers Mintlify's agent and human search
04What pricing information is available for Chroma?
Starter | $0/month | 10 databases, 10 team members, Community Slack · Team | $250/month | 100 databases, 30 team members, Slack support, SOC II, volume-based di
Starter - $0 + usage - 10 databases - 10 team members - Community Slack
Search API and GroupBy available in Python, JavaScript/TypeScript, and Rust SDKs · Collection forking available via Python and JS SDKs and the REST API (OpenAPI spec) · CloudClient in JS/TS client v3 lets Chroma Cloud users connect easily
Group By & Aggregation is available now in the latest versions of our Python, JavaScript, and Rust SDKs.
Client can be deployed on serverless providers such as Vercel, recommended with hosted emb
Easier to deploy on serverless providers like Vercel (Recommended to use with hosted embedding providers like OpenAI or Voyage AI instead of default embedding function).
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.
Common use cases
Powering agent and human search for AI-driven developer documentation platforms
Hybrid search combining SPLADE sparse vectors with dense vectors for high recall
Multi-tenant architectures with hundreds of thousands of collections in one database
Diversification and deduplication of results by metadata keys
Serverless deployment on Vercel with hosted embedding providers like OpenAI or Voyage AI
Powers agent and human search for AI-driven developer documentation platforms (e.g., Mintl
Starter | $0/month | 10 databases, 10 team members, Community Slack · Team | $250/month | 100 databases, 30 team members, Slack support, SOC II, volume-based di
API
Not publicly listed
Source links
17 recorded
Source-backed
Verified facts
Updated September 1, 2026
Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.
Built on object storage (S3 / GCS) with intelligent query-aware tiering
Deployment
BYOC in your VPC supported
View 32 more verified facts
Deployment
Multi-cloud and multi-region replication with point-in-time recovery
Audience
Developers (27k GitHub stars)
Pricing
Starter | $0/month | 10 databases, 10 team members, Community Slack
Pricing
Team | $250/month | 100 databases, 30 team members, Slack support, SOC II, volume-based discounts
Security
Practical capabilities
What it helps with
8 documented areas
A concise view of the jobs, capabilities and integrations described in the recorded product sources.
Use case
Powering agent and human search for AI-driven developer documentation platforms
Use case
Hybrid search combining SPLADE sparse vectors with dense vectors for high recall
Use case
Multi-tenant architectures with hundreds of thousands of collections in one database
Use case
Diversification and deduplication of results by metadata keys
Use case
Serverless deployment on Vercel with hosted embedding providers like OpenAI or Voyage AI
Use case
Powers agent and human search for AI-driven developer documentation platforms (e.g., Mintl
Use case
GroupBy enables diversification, deduplication by metadata keys like document_id, and mult
Use case
Indexing product docs, change logs, support pages, blogs, or any other web source used by
Availability
Where it runs and where to get it
Source checked
Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.
Cost / license
Starter | $0/month | 10 databases, 10 team members, Community Slack · Team | $250/month | 100 databases, 30 team members, Slack support, SOC II, volume-based diApache 2.0trueChroma is open-source search infrastructure for AI
Application types
Vector search / retrieval infrastructure for AI applications
Platforms
Chroma Cloud (managed cloud deployment of Chroma).Chroma Cloud Dashboard UI supports regex search and forkingJavaScript/TypeScript client v3 published as chromadb (npm/pnpm/bun) with smaller bundle sIndexingStatus is available on Chroma CloudMetadata arrays are supported across Python, TypeScript, and Rust in both K-expression andChroma Cloud
DeploymentBYOC in your VPC supported · Multi-cloud and multi-region replication with point-in-time recovery · Generally available on GCP and AWS for enterprise customers. · Forking is cloud-only and available to Chroma Cloud users and open-source users of Chroma
LicenseApache 2.0
Model supportNot disclosed by source
Data controlSOC 2 Type II examination completed · Customer data encrypted in transit and at rest using TLS/SSL, PKI, and AES · SOC 2 Type II certified. · SSO integration available. · Customer-Managed Encryption Keys (CMEK) generally available, plus BYOC support; default en
Learning curveIntermediate
Primary use casesPowering agent and human search for AI-driven developer documentation platforms, Hybrid search combining SPLADE sparse vectors with dense vectors for high recall, Multi-tenant architectures with hundreds of thousands of collections in one database, Diversification and deduplication of results by metadata keys, Serverless deployment on Vercel with hosted embedding providers like OpenAI or Voyage AI, Powers agent and human search for AI-driven developer documentation platforms (e.g., Mintl, GroupBy enables diversification, deduplication by metadata keys like document_id, and mult, Indexing product docs, change logs, support pages, blogs, or any other web source used by
What to verify before adopting
Collection Forking is currently cloud-only (Chroma Cloud and Chroma Distributed); single-n
Embedding functions are no longer bundled in the JS client and must be individually instal
Evolution and major updates
Chroma timeline
A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.
4 dated updates
Latest first · exact dates
Showing the newest updates and meaningful milestones. Open an entry for its summary and source.
Release note
EU Region Support
Open details
Chroma Cloud databases can now run in GCP europe-west1 in addition to AWS us-east-1, with full API parity and EU data residency for compliance.
Serverless data ingestion for Chroma Cloud that connects Amazon S3, GitHub repositories, and websites, with parsing, chunking, and embedding handled automatically.
Chroma SDKs (Python, TypeScript, Rust) now support storing arrays of strings, numbers, and booleans in metadata, queryable with $contains and $not_contains operators.
Chroma Cloud now exposes IndexingStatus via get_indexing_status(), reporting num_indexed_ops, num_unindexed_ops, total_ops, and op_indexing_progress so users can track write-ahead-log indexing.
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.
Customer data encrypted in transit and at rest using TLS/SSL, PKI, and AES
Company
Chroma Inc.
Headquarters
San Francisco, California (2261 Market Street #4728, San Francisco, CA 94114)
Mission
Building the data and search infrastructure for AI agents that need the right context, extremely quickly, with as little infrastructure concerns as possible.
Use case
Powers agent and human search for AI-driven developer documentation platforms (e.g., Mintlify).
Capability
Hybrid search combining native SPLADE (sparse vector keyword) support with dense vectors for improved recall.
Capability
Single database designed to hold hundreds of thousands of collections, enabling one-collection-per-customer architectures.
Capability
Built for high availability to eliminate recurring oncall incidents (e.g., reported P99 latency consistently bounded under 100ms with no spikes).
Platform
Chroma Cloud (managed cloud deployment of Chroma).
Deployment
Generally available on GCP and AWS for enterprise customers.
Security
SOC 2 Type II certified.
Security
SSO integration available.
Security
Customer-Managed Encryption Keys (CMEK) generally available, plus BYOC support; default encryption-at-rest is managed by Chroma.
Capability
Open-source search infrastructure for AI
Capability
Regex search support with $regex and $not_regex operators on the where_document field in .query or .get
Capability
GroupBy & Aggregation available on Chroma Cloud
Capability
GroupBy supports diversification, deduplication, and multi-key sorting via MinK or MaxK aggregation functions
Use case
GroupBy enables diversification, deduplication by metadata keys like document_id, and multi-key sorting with tie-breaking by priority or rating alongside vector similarity score
Capability
Collection Forking on Chroma Cloud using copy-on-write in 100-200ms, skipping the time and cost of re-indexing
Capability
Forked collections share data with the parent and only incur additional storage costs for incremental changes
Api
Search API and GroupBy available in Python, JavaScript/TypeScript, and Rust SDKs
Api
Collection forking available via Python and JS SDKs and the REST API (OpenAPI spec)
Platform
Chroma Cloud Dashboard UI supports regex search and forking
Deployment
Forking is cloud-only and available to Chroma Cloud users and open-source users of Chroma Distributed (single-node not yet supported)
Capability
ReadLevel parameter on the Search() API for explicit per-query consistency/latency control
Capability
IndexAndWal (default) reads from the index and incorporates recent, unindexed writes
Capability
IndexOnly reads strictly from the index, ignoring the WAL for faster, more consistent query latency
AI infrastructure · ToolBraintrustBraintrust is an enterprise-grade AI observability and evaluation platform for tracing production LLM applications, running experiments on datasets, comparing prompts and models, and catching regressions via online scoring and quality gates.Also mapped to AI infrastructure
AI infrastructure · ToolCerebriumCerebrium is a serverless AI infrastructure platform for real-time, high-performance applications. It provides global, region-aware GPU deployment, sub-second cold starts, instant autoscaling, and hardened gVisor workload isolation, with support for voice agents, video models, LLMs, multimodal pipelines, and large-scale batch jobs.Also mapped to AI infrastructure
AI infrastructure · ToolChromaChroma 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.Also mapped to AI infrastructure
AI infrastructure · ToolChronosphereFind and fix customer-impacting issues faster and stop paying for data you don’t use. Chronosphere is the world’s most reliable observability platform for microservices and containers.Also mapped to AI infrastructure
