Overview
Composio is the official SDK for the Composio platform, available for both Python and TypeScript. It lets you give AI agents a set of tools so they can take real actions, such as reading a Hacker News post or calling another app's API, instead of only generating text.
Rather than writing custom integration code for each agent framework, you fetch a toolkit through Composio and pass those tools straight into your agent. The SDK works with many frameworks and model providers, including OpenAI, OpenAI Agents, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, the Vercel AI SDK, Google Gemini, and Mastra.
What it does
- Official SDKs for both Python (3.10+) and TypeScript, the latter usable in Node.js and browser environments with full type definitions.
- Provider packages that plug Composio tools into popular agent frameworks like OpenAI Agents, Anthropic, LangChain, LangGraph, LlamaIndex, CrewAI, and AutoGen.
- Toolkit-based access: pull a named toolkit (for example HACKERNEWS) and hand the returned tools directly to your agent.
- Per-user tool calls through a user_id, so tools are fetched in the context of a specific end user.
- Custom provider support to integrate Composio with any AI framework that is not already covered.
- OpenAPI-based specification that the SDK documentation is generated from and can be refreshed during the build.
Getting started
Composio ships as separate Python and TypeScript SDKs. Install the core package, initialize the client, then add a provider package for the agent framework you use.
Install the core SDK
Use pip or poetry for Python, or npm, yarn, or pnpm for TypeScript.
pip install composio
# or
npm install @composio/coreInitialize the client (Python)
Create a Composio client. You can pass an API key, or rely on environment configuration.
from composio import Composio
composio = Composio(
# api_key="your-api-key",
)Add a provider and fetch tools
Install the provider package for your framework, then fetch a toolkit and pass the tools to your agent. This example uses the OpenAI Agents provider.
pip install composio_openai_agents openai-agentsBuild and run an agent
Get tools for a user and toolkit, attach them to an agent, then run the agent.
from agents import Agent, Runner
from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
composio = Composio(provider=OpenAIAgentsProvider())
user_id = "user@acme.org"
tools = composio.tools.get(user_id=user_id, toolkits=["HACKERNEWS"])
agent = Agent(
name="Hackernews Agent",
instructions="You are a helpful assistant.",
tools=tools,
)Commands and code are distilled from the project's own documentation — always check the official repo for the latest.
When to use it
- Give an agent built with OpenAI Agents, LangChain, CrewAI, or another supported framework the ability to call external apps and APIs.
- Fetch a ready-made toolkit, such as Hacker News, and let an agent answer questions using live data from that service.
- Avoid writing custom integration glue for each framework by sharing one tooling layer across Python and TypeScript projects.
- Build a custom provider to bring Composio tools into an AI framework that is not supported out of the box.
How Composio compares
Composio alongside other open-source agent frameworks & builders tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| AutoGPT | ★ 185k | One of the earliest autonomous agent projects, now a platform for building and running agents from reusable blocks and workflows. |
| Agno | ★ 40.8k | A fast Python framework (formerly Phidata) for building agents with memory, tools, and multimodal inputs, plus a runtime for deploying them in production. |
| AgentGPT | ★ 36.2k | AgentGPT lets you name a custom AI, give it a goal, and watch it plan tasks, run them, and learn from the results, all from a web browser. |
| LangGraph | ★ 35.2k | A library from the LangChain team for building stateful, graph-based agent workflows with explicit control over steps, memory, and human-in-the-loop checkpoints. |
| Composio | ★ 28.9k | Tooling SDK that connects AI agents to external apps and APIs |
| Semantic Kernel | ★ 28.2k | Microsoft's SDK for adding agents, plugins, and planning to apps across .NET, Python, and Java. |
| smolagents | ★ 27.9k | A minimal agent library from Hugging Face where the model writes and runs Python code to call tools and complete tasks. |
| Mastra | ★ 25.3k | A TypeScript framework for building AI agents and applications with workflows, RAG, memory, and observability built in. |