
Composio connects AI assistants and custom agents to apps such as Gmail, Slack, GitHub, and Linear. It's for people who want their assistant to act on requests across apps, and developers who don't want to maintain each integration themselves. Its CLI gives coding agents a local interface; the standard setup uses Composio's hosted authentication and execution service. It requires an account and internet access.
The platform finds relevant actions as a task unfolds instead of loading the entire tool catalogue into the model's context. For longer tasks, an isolated remote sandbox holds code, files, and intermediate results, keeping large responses out of the conversation. Agents can chain app actions with model calls and retain session state across turns. App triggers let agents respond to events.
Composio manages OAuth sign-in, API keys, and token refresh, with granular permissions for connected accounts. You can reuse connections across assistants, connect multiple accounts for the same app, and disconnect them when needed. Credentials and sensitive customer data are encrypted at rest and in transit.
It works with Claude, Codex, ChatGPT, Cursor, and assistants that accept MCP servers. Custom MCP servers can extend its app connections. Developers get open source Python and TypeScript SDKs under the MIT license, plus adapters for frameworks including OpenAI Agents, Claude Agent SDK, LangGraph, and Vercel AI SDK. A managed MCP gateway provides a shared endpoint for tools and agents.
Separately arranged deployments can run Composio in your own environment with vendor-provided Helm support. The MIT SDK repository does not provide the full self-hosted platform; deployment terms and operations are arranged with Composio.
Claim this page with an email at composio.dev. Composio gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Composio?Promote it
Something wrong or outdated on this page?
8.5KUpdated 23 hours agoApache-2.0
Web#LLM tracing#MCP#Multimodal input
Bifrost is a self-hosted AI gateway for developers and teams whose applications use multiple model providers. It puts Ollama, custom model deployments, and cloud services behind one OpenAI-compatible API, so applications can switch models without maintaining a separate integration for each provider.
62.5KUpdated 1 day agoMIT
#MCP#RAG#Tool calling
27.3KUpdated 20 hours agoMIT
macOS · Windows · Linux#Code execution#MCP#Tool calling
27.9KUpdated 1 day agoApache-2.0
#MCP#Structured output#Tool calling
13KUpdated 22 hours agoApache-2.0
Docker#Agent Skills#Hugging Face integration#Knowledge graphs
31.3KUpdated 1 day agoApache-2.0
Docker#Hybrid search#Knowledge graphs#llama.cpp backend
Context7 brings current library documentation and code examples into an AI coding assistant's context. It's for developers who want answers grounded in the libraries and versions they're actually using, rather than an assistant's older training data. It works with Claude Code, Codex, Cursor, Devin Desktop and Antigravity.
Cua gives AI agents access to computers they can inspect and operate, with tools for desktop automation, local virtual machines, and hosted fleets. It's for developers building agents that work across native apps and browsers, or evaluating how well those agents complete computer tasks. You bring the agent and model.
FastMCP is an open-source Python framework for developers connecting AI agents to their own tools and data through the Model Context Protocol (MCP). It supports locally running servers and connections to remote servers, with server development and client access in the same framework. It uses the Apache 2.0 license.
txtai is a Python framework for developers building search applications, chat with their data, and AI agents on their own hardware or servers. Its embeddings database combines sparse and dense vector search with graphs and relational data, so the same system can find related content and supply context to language models. It's open source under Apache 2.0.
Graphiti is a self-hosted Python framework for developers building AI agents that need to remember changing facts. It builds knowledge graphs from conversations, structured records and unstructured text, so an agent can query current information or recover what was true earlier. It's open source under Apache 2.0.