Composio
Tool integration platform connecting AI agents to 250+ external services
View on GitHubWhat it solves
The 1000-line tool problem: connecting an agent to real external services without writing a bespoke OAuth handler, webhook listener, and schema normalizer for every API.
Overview
Composio is an integration layer that gives AI agents normalized access to external services (GitHub, Slack, Gmail, Jira, Linear, Notion, and 250+ more) through a single Python or TypeScript client. It handles OAuth flows, credential storage, and action schema normalization so every tool looks the same to the agent regardless of the underlying API. Works with LangChain, CrewAI, AutoGen, the OpenAI Agents SDK, and raw function calls.
Key facts
- Language
- TypeScript
- License
- MIT
- Maturity
- Fast-moving
- Maintainer
- ComposioHQ
- Reviewed
- 2026-06-11
Where to start
The Python README explains the action model, how every external service exposes a typed, discoverable set of actions the agent can query and invoke.
python/README.mdTechnologies
More in this domain
LangGraph
Stateful multi-agent orchestration for LLM applications
The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.