Files
Rahul Tarak caef908075 docs: refresh README(s) (#3801)
## Summary

Rewrites the stale root `README.md` against the current docs (structure
modeled on [earendil-works/pi](https://github.com/earendil-works/pi)'s
README).

- **Quickstarts** now use the session-based API (`composio.create()` →
`session.tools()`) that the docs treat as canonical, replacing the
legacy `composio.tools.get()` flow
- **Positioning** matches the docs welcome page: 1000+ pre-authenticated
toolkits, per-user sessions, auth, triggers, and a sandbox
- **New sections**: CLI install (curl / Homebrew / npm),
sessions-via-MCP note, repository layout, minimum runtime versions
- **Provider table** merged with package links; adds the Claude Agent
SDK providers (both SDKs) and the experimental Pi provider
(`@composio/experimental`); documents the Python
`composio-gemini`/`composio-google`/`composio-google-adk` split
- **Removed**: Rube section (no longer in docs), cover banner (replaced
with theme-adaptive brand logomark from brand.composio.dev),
master-branch pointer, internal OpenAPI-pull section, private
`@composio/ts-builders` listing

Docs-only change — no changeset needed.

## Preview

Rendered view: [README.md on this
branch](https://github.com/ComposioHQ/composio/blob/docs/refresh-root-readme/README.md)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-10 06:14:38 -07:00

1.5 KiB

composio-llamaindex

Adapts Composio tools to LlamaIndex's FunctionTool format so a LlamaIndex agent can call 1000+ apps through a single Composio session.

Installation

pip install composio composio-llamaindex llama-index llama-index-llms-openai

Set COMPOSIO_API_KEY (get one from dashboard.composio.dev/settings) and OPENAI_API_KEY in your environment:

export COMPOSIO_API_KEY=xxxxxxxxx
export OPENAI_API_KEY=xxxxxxxxx

Quickstart

Create a session for your user, fetch its tools, and hand them to a FunctionAgent. LlamaIndex drives the tool calls; each tool executes itself through Composio.

import asyncio

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

composio = Composio(provider=LlamaIndexProvider())
llm = OpenAI(model="gpt-5.2")

# Each session is scoped to one of your users
session = composio.create(user_id="user_123")
tools = session.tools()

agent = FunctionAgent(tools=tools, llm=llm)


async def main():
    result = await agent.run(
        user_msg="Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'"
    )
    print(result)


asyncio.run(main())