Chroma

Chroma (Chroma DB) is an open-source AI-native embedding database designed to make it easy to build LLM applications by providing storage, retrieval, and management for vector embeddings, full-text search, regex search, and multi-modal retrieval (text, image, audio). Distributed under the Apache 2.0 license, Chroma can be self-hosted (single-node Python or distributed Rust-based deployment) or consumed via Chroma Cloud, a managed serverless vector database service offering usage-based pricing. Chroma is the open-source data infrastructure for AI agents and RAG (Retrieval-Augmented Generation) applications, with first-party SDKs for Python and JavaScript/TypeScript and integrations with leading embedding providers (OpenAI, Cohere, Hugging Face, sentence-transformers).

Chroma publishes 9 API contracts indexed on the APIs.io network, including Collections API, Databases API, Records API, and 6 more. Tagged areas include Artificial Intelligence, AI-Native, Apache 2.0, Cloud, and Embeddings.

The Chroma catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

Chroma’s developer surface includes authentication, documentation, developer portal, pricing, engineering blog, and 25 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

51.5/100 developing ▬ flat Agent 32/100 agent ready Front door AI 5/6 prominent saas · Apache License 2.0 Full breakdown ↓
scored 2026-10-17 · rubric v0.24.0

AccessPaid

2 published contracts 1 MCP Servers 10 Features 8 Use Cases

Artificial Intelligence AI-Native Apache 2.0 Cloud Embeddings Hybrid Search JavaScript LLM Machine Learning Multi-Modal Open Source Python RAG Retrieval SDK Search Serverless TypeScript Vector Database Database Vector Search

Kin Score

Kin Score How this is scored →
scored 2026-10-17 · rubric v0.24.0

Composite quality — 51.5/100 · developing

Contract Quality 10.0 / 19

Developer Ergonomics 7.0 / 15

Access Clarity 10.1 / 15

Operational Transparency 2.6 / 10

Contract Governance 0.9 / 9

Discoverability 5.0 / 8

Regulatory Posture 4.4 / 15

Create-or-Update Ergonomics 3.3 / 10

Agent readiness — 32/100 · agent ready

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 12 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Regulatory Posture applies to this provider. Its tags matched the AI & Biometrics regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/chroma: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
Retrieval, Vector and RAG	covered	34.0	-	-

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

APIs 9

Individual APIs this provider publishes, each with its own machine-readable definition.

Chroma Python Client

The Chroma Python Client is a first-party SDK for interacting with both self-hosted Chroma servers and Chroma Cloud. It provides a simple, developer-friendly interface with a co...

Chroma JavaScript Client

The Chroma JavaScript and TypeScript Client is a first-party SDK for interacting with Chroma from JavaScript or TypeScript applications. The v3 rewrite focused on reducing bundl...

Chroma Collections API

Collection management endpoints for creating, listing, retrieving, updating, and deleting collections within a database.

Chroma Databases API

Database management endpoints for creating, listing, retrieving, and deleting databases within a tenant.

Chroma Records API

Record management endpoints for adding, getting, updating, upserting, deleting, and querying records within a collection.

Chroma Search API

Advanced search endpoints available exclusively in Chroma Cloud. Provides a unified interface for hybrid search operations combining vector similarity search with metadata filte...

Chroma System API

System-level endpoints for health checks, version information, and server diagnostics.

Chroma Tenants API

Tenant management endpoints for creating and retrieving tenants.

Chroma Query API

Chroma Cloud Collections Tenants API

OPEN COLLECTION

Scroll for all 10

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

Chroma MCP Server

Remote MCP server at mcp.trychroma.com over HTTP; 3 tools listed.

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Chroma Plans Pricing

9 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Chroma Rate Limits

2 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Chroma Finops

FINOPS

Features 10

Notable capabilities this provider offers.

Document and Metadata Storage

Vector Similarity Search (Dense, Sparse, Hybrid)

Full-Text and Regex Search

Metadata Filtering

Multi-Modal Retrieval (Text, Image, Audio)

Automatic Tokenization and Embedding

Collection Management

Embedding Function Plugins

Self-Hosted and Cloud Deployments

Apache 2.0 Open Source License

Scroll for all 10

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Chroma Context

0 classes · 6 properties

JSON-LD

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Chroma — jsonschema rules

6 rules · 4 warnings 2 info

SPECTRAL

JSON Schema 2

Standalone JSON Schema definitions for this provider's data models.

Chroma Collection

5 properties

JSON SCHEMA

Chroma Record

5 properties

JSON SCHEMA

Security Posture 4

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Chroma Authentication

apiKey/http · 3 schemes

SECURITY

Chroma Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Chroma Vulnerability Disclosure

no policy recorded

SECURITY

Chroma Trust Center

SOC 2, ISO 27001

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Chroma Agentic Access

25 operations · 11 acting · 1 human-in-the-loop

25 operations · 11 acting

AGENTIC

Use Cases 8

What developers build with this provider.

RAG (Retrieval Augmented Generation)

Semantic Search

AI Agent Memory

Code Search (AST-Aware Chunking)

Recommendation Systems

Multi-Modal Search (Text + Images)

Question Answering Systems

Knowledge Base Querying

Scroll for all 8

Resources

Get Started 2

Portal, sign-up, and the first successful call

Portal

Portal

Login

Documentation 3

Reference material describing how the API behaves

Documentation

Documentation

JSONSchema

JSONSchema

JSONSchema

JSONSchema

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

LlmsText

LlmsText

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

JSONLDContext

JSONLDContext

Spectral

Spectral

Build 3

SDKs, sample code, and the tooling you integrate with

PostmanWorkspace

PostmanWorkspace

GitHubOrg

GitHubOrg

SourceCode

SourceCode

Access & Security 4

Authentication, authorization, and security posture

TrustCenter

TrustCenter

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 4

Status, limits, changes, and where to get help

RateLimits

IssueTracker

Releases

Discord

Commercial 6

Pricing, plans, and the legal terms of use

FinOps

Plans

Pricing

License

TermsOfService

PrivacyPolicy

Company 4

The organization behind the API

LinkedIn

Website

Website

Blog

Blog

Twitter

Twitter

Other 2

Properties that don't map to a standard resource type

Source (apis.yml)

aid: chroma
name: Chroma
kind: company
description: Chroma (Chroma DB) is an open-source AI-native embedding database designed to make it easy to build LLM applications
  by providing storage, retrieval, and management for vector embeddings, full-text search, regex search, and multi-modal retrieval
  (text, image, audio). Distributed under the Apache 2.0 license, Chroma can be self-hosted (single-node Python or distributed
  Rust-based deployment) or consumed via Chroma Cloud, a managed serverless vector database service offering usage-based pricing.
  Chroma is the open-source data infrastructure for AI agents and RAG (Retrieval-Augmented Generation) applications, with
  first-party SDKs for Python and JavaScript/TypeScript and integrations with leading embedding providers (OpenAI, Cohere,
  Hugging Face, sentence-transformers).
url: https://raw.githubusercontent.com/api-evangelist/chroma/refs/heads/main/apis.yml
type: Index
deliveryModel:
  model: saas
  license: Apache License 2.0
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - license
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: paid
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Paid
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
position: Consuming
access: 3rd-Party
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/chroma.png
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-09-21
x-docs-hosting: vercel
tags:
- Artificial Intelligence
- AI-Native
- Apache 2.0
- Cloud
- Embeddings
- Hybrid Search
- JavaScript
- LLM
- Machine Learning
- Multi-Modal
- Open Source
- Python
- RAG
- Retrieval
- SDK
- Search
- Serverless
- TypeScript
- Vector Database
- Database
- Vector Search
tags_raw:
- AI
- AI Native
- Apache 2.0
- Cloud
- Embeddings
- Hybrid Search
- JavaScript
- LLM
- Machine Learning
- Multi-Modal
- Open Source
- Python
- RAG
- Retrieval
- SDK
- Search
- Serverless
- TypeScript
- Vector Database
- Machine-Learning
- Open-Source
- Database
- Vector Search
created: '2025-03-07'
modified: '2026-05-19'
specificationVersion: '0.23'
apis:
- aid: chroma:python-client
  name: Chroma Python Client
  description: The Chroma Python Client is a first-party SDK for interacting with both self-hosted Chroma servers and Chroma
    Cloud. It provides a simple, developer-friendly interface with a core API of just four functions for managing collections,
    adding documents, and querying embeddings. The client handles automatic tokenization, embedding, and indexing of documents,
    making it straightforward to build AI applications that require vector similarity search.
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.trychroma.com/reference/python/client
  tags:
  - Embeddings
  - Python
  - SDK
  - Vector Database
  properties:
  - type: Documentation
    url: https://docs.trychroma.com/reference/python/client
  - type: SourceCode
    url: https://github.com/chroma-core/chroma
- aid: chroma:javascript-client
  name: Chroma JavaScript Client
  description: The Chroma JavaScript and TypeScript Client is a first-party SDK for interacting with Chroma from JavaScript
    or TypeScript applications. The v3 rewrite focused on reducing bundle size and improving developer experience, making
    it well-suited for deployment on serverless platforms like Vercel. It supports both self-hosted Chroma instances and Chroma
    Cloud via the CloudClient class, providing collection management, document ingestion, and vector similarity search capabilities.
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.trychroma.com/reference/js/client
  tags:
  - Embeddings
  - JavaScript
  - SDK
  - TypeScript
  - Vector Database
  properties:
  - type: Documentation
    url: https://docs.trychroma.com/reference/js/client
  - type: SourceCode
    url: https://github.com/chroma-core/chroma-js
- aid: chroma:chroma-collections-api
  name: Chroma Collections API
  description: Collection management endpoints for creating, listing, retrieving, updating, and deleting collections within
    a database.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - Collection
  tags_raw:
  - Collections
  properties:
  - type: OpenAPI
    url: openapi/chroma-collections-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-databases-api
  name: Chroma Databases API
  description: Database management endpoints for creating, listing, retrieving, and deleting databases within a tenant.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - Database
  tags_raw:
  - Databases
  properties:
  - type: OpenAPI
    url: openapi/chroma-databases-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-records-api
  name: Chroma Records API
  description: Record management endpoints for adding, getting, updating, upserting, deleting, and querying records within
    a collection.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - Records
  properties:
  - type: OpenAPI
    url: openapi/chroma-records-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-search-api
  name: Chroma Search API
  description: Advanced search endpoints available exclusively in Chroma Cloud. Provides a unified interface for hybrid search
    operations combining vector similarity search with metadata filtering and custom ranking expressions.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - Search
  properties:
  - type: OpenAPI
    url: openapi/chroma-search-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-system-api
  name: Chroma System API
  description: System-level endpoints for health checks, version information, and server diagnostics.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - System
  properties:
  - type: OpenAPI
    url: openapi/chroma-system-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-tenants-api
  name: Chroma Tenants API
  description: Tenant management endpoints for creating and retrieving tenants.
  humanURL: https://docs.trychroma.com/reference/chroma-reference
  baseURL: https://api.trychroma.com
  tags:
  - Tenants
  properties:
  - type: OpenAPI
    url: openapi/chroma-tenants-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: Documentation
    url: https://docs.trychroma.com/cloud/sync/overview
- aid: chroma:chroma-query-api
  name: Chroma Query API
  description: Nearest-neighbor vector similarity search over a collection.
  humanURL: https://docs.trychroma.com/reference/python/client
  baseURL: https://api.trychroma.com
  tags:
  - Query
  properties:
  - type: OpenAPI
    url: openapi/chroma-query-api-openapi.yml
  - type: Documentation
    url: https://docs.trychroma.com/docs/collections/manage-collections
  - type: APIReference
    url: https://docs.trychroma.com/reference/chroma-reference
  - type: PostmanCollection
    url: collections/chroma-db.postman_collection.json
  - type: OpenCollection
    url: collections/chroma-db.opencollection.json
  - type: Documentation
    url: https://docs.trychroma.com/docs/collections/add-data
  - type: APIReference
    url: https://docs.trychroma.com/reference/chroma-api/record/add-records
  - type: Documentation
    url: https://docs.trychroma.com/docs/querying-collections/query-and-get
  - type: APIReference
    url: https://docs.trychroma.com/reference/chroma-api/record/query-collection
  - type: Documentation
    url: https://docs.trychroma.com/docs/overview/architecture
common:
- type: RateLimits
  url: rate-limits/chroma-rate-limits.yml
- type: FinOps
  url: finops/chroma-finops.yml
- type: Plans
  url: plans/chroma-plans-pricing.yml
- type: IssueTracker
  url: https://github.com/chroma-core/chroma/issues
- type: Releases
  url: https://github.com/chroma-core/chroma/releases
- type: PostmanWorkspace
  url: https://www.postman.com/kinlaneapi/chroma/overview
- type: AgenticAccess
  url: agentic-access/chroma-agentic-access.yml
- type: TrustCenter
  url: security/chroma-trust-center.yml
- type: VulnerabilityDisclosure
  url: security/chroma-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/chroma-domain-security.yml
- type: Authentication
  url: authentication/chroma-authentication.yml
- type: LinkedIn
  url: https://www.linkedin.com/company/trychroma
- type: Website
  url: https://www.trychroma.com/
- type: Documentation
  url: https://docs.trychroma.com/docs/overview/introduction
- type: Portal
  url: https://docs.trychroma.com/
- type: Login
  url: https://cloud.trychroma.com/
- type: Pricing
  url: https://docs.trychroma.com/cloud/pricing
- type: Blog
  url: https://www.trychroma.com/blog
- type: GitHubOrg
  url: https://github.com/chroma-core
- type: SourceCode
  url: https://github.com/chroma-core/chroma
- type: Discord
  url: https://discord.gg/MMeYNTmh3x
- type: Twitter
  url: https://twitter.com/trychroma
- type: License
  name: Apache License 2.0
  url: https://github.com/chroma-core/chroma/blob/main/LICENSE
- type: TermsOfService
  url: https://www.trychroma.com/tos
- type: PrivacyPolicy
  url: https://www.trychroma.com/privacy
- type: JSONLDContext
  url: json-ld/chroma-context.jsonld
- type: JSONSchema
  url: json-schema/chroma-collection-schema.json
- type: JSONSchema
  url: json-schema/chroma-record-schema.json
- type: Spectral
  url: spectral/chroma-spectral.yml
- name: Features
  type: Features
  data:
  - name: Document and Metadata Storage
  - name: Vector Similarity Search (Dense, Sparse, Hybrid)
  - name: Full-Text and Regex Search
  - name: Metadata Filtering
  - name: Multi-Modal Retrieval (Text, Image, Audio)
  - name: Automatic Tokenization and Embedding
  - name: Collection Management
  - name: Embedding Function Plugins
  - name: Self-Hosted and Cloud Deployments
  - name: Apache 2.0 Open Source License
- name: EmbeddingProviders
  type: EmbeddingProviders
  data:
  - name: OpenAI
  - name: Cohere
  - name: Hugging Face
  - name: sentence-transformers
  - name: Google Vertex AI
  - name: Ollama
- name: UseCases
  type: UseCases
  data:
  - name: RAG (Retrieval Augmented Generation)
  - name: Semantic Search
  - name: AI Agent Memory
  - name: Code Search (AST-Aware Chunking)
  - name: Recommendation Systems
  - name: Multi-Modal Search (Text + Images)
  - name: Question Answering Systems
  - name: Knowledge Base Querying
- name: Standards
  type: Standards
  data:
  - name: OpenAPI Specification
  - name: REST/HTTP
  - name: Apache License 2.0
- type: LlmsText
  url: https://docs.trychroma.com/llms.txt
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/chroma"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/chroma/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/chroma/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.