open-agent-connector

Open-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP ac

What is open-agent-connector?

Open-source, self-hosted alternative to Composio, Nango, Merge.dev, and Arcade.dev for AI agent integrations. Run GitHub, Slack, Hacker News, and custom HTTP actions over MCP or REST.

Overview of open-agent-connector

What it is

Open Agent Connector is an open-source, self-hosted integration gateway for AI agents. It allows developers to connect accounts to application APIs, keep credentials in their own runtime, and let agents discover and run actions through the Model Context Protocol (MCP) or a REST API. The project is a self-hosted alternative to platforms like Composio, Nango, Merge.dev, and Arcade.dev. It currently registers 256 providers with 8,385 actions across categories such as Developer tools, Project Management, Communication, Storage, AI/ML, E-Commerce, Social Media, Financial, and Utilities.

Key features

  • MCP gateway: Model Context Protocol (MCP) JSON-RPC 2.0 endpoint over POST /mcp and tool discovery over GET /mcp/tools. Every remote MCP call fails closed and requires an admin or runtime token with granular scope enforcement.
  • Scoped runtime tokens: hashed, revocable tokens with deny-by-default action grants plus optional connection and proxy restrictions.
  • OAuth: authorization URL, state and code exchange, encrypted token storage, and refresh for providers that support OAuth.
  • Action discovery: agents can list providers, search actions, inspect action guides and schemas, and execute actions.
  • REST API: list providers and actions, execute an action, or use a provider proxy where supported.
  • Connections & credentials: save named provider connections; credential values are encrypted at rest with AES-256-GCM.
  • Local web console: browse the 256-provider catalog, configure connections, execute test runs, and manage runtime tokens and audit logs.

Use cases

Open Agent Connector is designed for developers who want to inspect, run, and extend their own agent integration layer. It can be used to connect AI agents to services such as GitHub, Slack, Hacker News, and custom HTTP actions. It is suitable for teams that need a self-hosted integration gateway with full control over credentials and runtime.

Getting started

Requirements: Python 3.11 or newer, Node.js and npm. Run the API: bash cd server python -m venv venv source venv/bin/activate python -m pip install -r requirements.txt uvicorn main:app --host 127.0.0.1 --port 8000 --reload On Windows PowerShell: powershell venvScriptsActivate.ps1 Run the web console (from repository root): bash cd client npm install npm run dev Open http://localhost:3000. The console uses http://localhost:8000 for the API by default.

License and pricing

Licensed under Apache-2.0. Open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/anil-matchaopen-agent-connector.svg)](https://yunodb.com/tools/anil-matchaopen-agent-connector?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/anil-matchaopen-agent-connector?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/anil-matchaopen-agent-connector.svg" alt="Featured on YunoDB" height="20"></a>