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.

What it solves

Composio simplifies the process of giving AI agents the ability to interact with external applications. It removes the friction of manually building and managing authentication, session handling, and tool definitions for hundreds of different apps, allowing developers to move from intent to action more quickly.

How it works

Composio provides a set of SDKs (TypeScript and Python) and a CLI that act as a bridge between AI agents and over 1,000 pre-authenticated toolkits. It uses a session-based system where each session is scoped to a specific user, managing their authentication and connected accounts. To avoid overloading an agent's context window with hundreds of tool definitions, Composio uses "meta tools" that allow agents to discover and execute tools at runtime. It also supports the Model Context Protocol (MCP) for compatibility with clients like Claude and Cursor.

Who it’s for

Developers building AI agents who need their agents to perform real-world tasks across a wide variety of third-party software applications.

Highlights

  • Massive Tool Library: Access to 1,000+ pre-authenticated toolkits.
  • Multi-Framework Support: Dedicated provider adapters for OpenAI, Anthropic, LangChain, LlamaIndex, CrewAI, AutoGen, and more.
  • User-Centric Sessions: Per-user session management for secure, scoped authentication.
  • CLI Tooling: A command-line interface for searching, executing, and scripting tools directly from the shell.
  • MCP Integration: Hosted MCP endpoints for seamless integration with MCP-compatible clients.

Related

  • Project
    UsefulSoftwareCo/executor

    An open-source integration layer that centralizes tool configurations, authentication, and policies for AI agents via the Model Context Protocol (MCP).

  • Project
    docker/compose-for-agents

    A collection of Docker Compose templates that simplify the deployment and testing of various AI agent frameworks by automating environment and model configuration.

  • Project
    compozy/compozy

    An operating system for AI agents that provides a persistent runtime environment with automation, supervision, and state management for ACP-compatible agent CLIs.

  • Project
    aipotheosis-labs/aci

    ACI.dev is an open-source tool-calling platform that provides unified, secure access to over 600 external services for AI agents, simplifying authentication and integration management.

  • Project
    mondaycom/mcp

    An open framework and MCP server that enables AI agents to securely interact with monday.com to manage projects, track tasks, and execute workflows.