Ross ROSS = Recommend OSS · open-source software intelligence for agents

ComposioHQ/composio

Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action. observed · 2026-08-28

github.com/ComposioHQ/composio · homepage · TypeScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

88/100

  • Activity 99
  • Release rhythm 87
  • Longevity 65
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 922
  • days_rel: 10
  • days_push: 7
  • n_releases_24m: 692

Full methodology

Adoption not part of the score

29893 stars · 4748 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Composio is an SDK platform (TypeScript and Python SDKs plus a CLI) that gives AI agents access to 1000+ pre-built app toolkits with per-user authentication, tool search, triggers, and sandboxed execution. It exposes sessions with meta-tools for runtime tool discovery and offers provider adapters for OpenAI, Anthropic, LangChain, CrewAI, Vercel AI SDK, and MCP clients.

Use cases

  • give my AI agent access to Gmail, Slack, and GitHub tools
  • manage OAuth authentication for multiple users in an agent app
  • let my coding agent connect to SaaS apps via MCP
  • find and execute app tools dynamically without loading all schemas
  • build an agent that takes actions across 1000+ apps
  • add triggers so my agent reacts to events like new emails
  • use toolkits with LangChain or CrewAI agents

When to choose

  • you're building production AI agents that need authenticated access to many third-party apps
  • you want per-user credential management handled for you instead of implementing OAuth flows
  • you need runtime tool discovery to avoid stuffing hundreds of tool schemas into model context
  • you use a supported framework (OpenAI Agents, LangChain, CrewAI, Vercel AI SDK) and want drop-in tool integration

When to avoid

  • you only need one or two simple API integrations you can call directly
  • you require fully self-hosted infrastructure with no dependency on Composio's hosted platform and API key
  • your agent runs in an environment without Node.js 22+ (for the TypeScript SDK) or network access
  • you need strict data residency since tool execution and credentials flow through Composio's cloud

Facets

library · maturity active

agent-framework auth mcp sdk cli api-framework webhook large-language-models developer-tools apis security python cli cross-platform tool-integration function-calling oauth tool-discovery llmops sandboxed-execution triggers provider-adapters monorepo ai-agents automation nodejs typescript web-server

10 sources

Member repositories

RepositoryRoleHealth v2
ComposioHQ/composiomain88

For agents

markdown · JSON · MCP: product_card(name="ComposioHQ/composio")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem