open-connector

English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Русский | Français | Español

OpenConnector is an open-source connector gateway for AI agents and an alternative to Pipedream/Composio. Connect user app accounts once, then expose a shared catalog of 1,000+ providers and 10,000+ prebuilt Actions to agents and applications.

Managed OAuth and hosted runtime, ready to use. No deployment or OAuth app setup.	Run locally or on your own infrastructure with Docker or Node.js. You manage storage and OAuth apps.	Cloudflare, Fly.io, RepoCloud, nibrun, NEXUS AI, Pethost, ZopDay, and more.
🚀 OOMOL Hosted	Self-host	More platforms

Use the Connector SDK from app code, oo CLI as the local-agent relay, MCP from agent hosts, HTTP/OpenAPI from custom clients, and the Web Console for administration and debugging.

• Keep credentials, scopes, schemas, policies, and run logs inside an inspectable runtime.
• Run locally, on your own infrastructure, or through OOMOL's hosted runtime.
• Use the same provider ids, Action ids, schemas, and contracts across open-source and commercial SaaS deployments.

• A working connector catalog across products such as GitHub, Gmail, Notion, BigQuery, Google Analytics, Supabase, Airtable, Slack, and more.
• Credential handling for API keys, OAuth2, custom credentials, and no-auth providers.
• Built-in OAuth 2.1 authorization server so remote MCP clients and other agents can authenticate with dynamically registered clients, PKCE S256, and revocable, policy-scoped access tokens.
• Inspectable Action contracts: request/response schemas, required scopes, and lazy-loaded executor source.
• Runtime controls for connection identity, scopes, runtime tokens, action allow/block policies, temporary file transit, and redacted run logs.
• Deployment options for local Docker or Node.js with SQLite or PostgreSQL state and local or S3-compatible transit storage, plus OOMOL's hosted runtime. Additional managed platforms are listed in deployment options.

OpenConnector fits products where agents need durable access to the tools users already use, without handing provider credentials to the agent process.

• Agent products that need reusable access across work apps, developer tools, data systems, communication platforms, and AI services.
• Products adding agent workflows that need stable, inspectable Action contracts for user app access.
• Teams that want hosted auth for speed while keeping a path to private or self-hosted runtime control.

Endpoint details, response envelopes, auth headers, MCP tools, and Action guide examples are in docs/runtime-api.md.

OpenConnector ships with a local Dashboard for browsing connectors, configuring credentials, creating runtime tokens, and inspecting runtime usage.

Use the connector catalog to see available services, search for providers, and open their Actions and credential setup from one place.

Use the Overview page after deployment to monitor runtime readiness, available providers, executable Actions, recent failures, tool call trends, and recent calls.

Provider names and trademarks belong to their respective owners and are used only for identification and interoperability.

flowchart LR
  Agent["AI Agent / App"] -->|"SDK / CLI / MCP / HTTP"| Gateway["OpenConnector Gateway"]
  Gateway --> Auth["Credential & OAuth Boundary"]
  Gateway --> Catalog["Provider Catalog"]
  Gateway --> Actions["Open-source Action Executors"]
  Gateway --> Policy["Tokens, Scopes, Allow/Block Policy"]
  Gateway --> Logs["Run Logs"]
  Actions --> Providers["1,000+ Providers"]
  Console["Web Console"] --> Gateway
  Cloudflare["Cloudflare Workers, D1, R2"] -. deploy .-> Gateway

Apps and agents discover Actions, inspect schemas and scopes, select a connection alias, and execute through the gateway. Provider secrets stay behind the runtime boundary; agents receive the metadata, safe account labels, and execution results needed for the run.

Start the runtime from the published image with Docker Compose:

docker compose up

This pulls ghcr.io/oomol-lab/open-connector:latest. To build from source instead:

docker compose -f docker-compose.yml -f docker-compose.build.yml up --build

Open the local console and generated API reference:

http://localhost:3000
http://localhost:3000/docs

Run a no-auth Action to verify the runtime:

curl -s -X POST http://localhost:3000/v1/actions/hackernews.get_top_stories \
  -H 'content-type: application/json' \
  -d '{"input":{}}'

See docs/quickstart.md for the full local setup, first provider connection, OAuth flow, and runtime settings.

GitHub is the simplest credentialed example because it can use a personal access token:

curl -s -X PUT http://localhost:3000/api/connections/github \
  -H 'content-type: application/json' \
  -d '{"authType":"api_key","values":{"apiKey":"github_pat_..."}}'

curl -s -X POST http://localhost:3000/v1/actions/github.get_current_user \
  -H 'content-type: application/json' \
  -d '{"input":{}}'

A GitHub App installation works the same way with no token to paste: store the App ID, the installation id and the App's private key, and the runtime mints one-hour installation tokens on demand. The connection profile identifies the installation's account; get_current_user requires a personal access token or OAuth user credential. Installation repository listing supports pagination only; omit visibility, sort and direction.

curl -s -X PUT http://localhost:3000/api/connections/github \
  -H 'content-type: application/json' \
  -d "{\"authType\":\"custom_credential\",\"values\":{\"appId\":\"1234567\",\"installationId\":\"87654321\",\"privateKey\":\"$(awk 'BEGIN{ORS="\\n"}1' app.private-key.pem)\"}}"

For OAuth2 apps, named connections, credential encryption, token refresh, and action policies, see docs/credentials.md and docs/configuration.md.

For npm-based local development, open http://localhost:5173; the Web Console dev server proxies API requests to the runtime on http://localhost:3000. For Docker or a built Node runtime, the console is served from http://localhost:3000.

The console supports provider browsing, API key and OAuth client configuration, runtime token creation, Action schema inspection, Action debugging, recent run review, and access to the generated OpenAPI and MCP metadata.

The Node runtime uses SQLite by default and can use PostgreSQL 15 or newer when OOMOL_CONNECT_DATABASE_URL is configured. PostgreSQL migrations are explicit: run npm run runtime:migrate before starting a version with pending migrations. Server startup only checks schema readiness and never applies PostgreSQL DDL. See docs/configuration.md for configuration, permissions, TLS, and multi-instance requirements. The Docker image exposes the same runner as its migrate subcommand; see docs/docker-ghcr.md.

Run OpenConnector from a prebuilt image on GitHub Packages (GHCR): ghcr.io/oomol-lab/open-connector. Use latest for the newest release, a pinned released version for production, or tip for the latest main build.

See docs/docker-ghcr.md for tags, pulling, and running.

If you want an AI bot you can use out of the box, try Leina. Leina connects to over 1,500 SaaS apps and lets you customize your own AI agent by choosing its app connections, skills, and knowledge base to fit your team’s workflows.

Use it in Slack, Microsoft Teams, Discord, or Telegram to find information, compile weekly reports, organize customer feedback, and prepare sales follow-ups through the apps you authorize.

• Quickstart
• Developer tools
• Programmatic connection management
• Connect your clients: MCP, CLI, and SDK
• Gmail OAuth and SDK tutorial
• Instagram OAuth and Actions
• Runtime API and MCP
• Embed the runtime (@oomol-lab/open-connector)
• Deployment options
• Fly.io deployment
• Cloudflare deployment
• Docker image (GHCR)
• Single binary
• Configuration
• Credentials and OAuth
• Catalog format
• Verification language
• Contributing
• Code of Conduct
• Security

Use Node.js 22.23.4+, 24.22.1+, or 26.12.1+ within those release lines. See the runtime security baseline before deploying:

npm install
npm run dev

The local API runtime listens on http://localhost:3000. The Web Console dev server listens on http://localhost:5173 and proxies API requests to the runtime.

Before opening a pull request:

npm run fix-check
npm test

Provider code lives under src/providers/<service>. See CONTRIBUTING.md for provider contribution rules.

Unless otherwise noted, the source code, scripts, generated project scaffolding, tests, and documentation authored for this repository are licensed under the OpenConnector License, a modified Apache License 2.0. See LICENSE.txt.

You may use, modify, and self-host OpenConnector for any purpose, including commercial use and embedding it in your own products. The one added condition is that providing OpenConnector to third parties as a hosted connector service requires a commercial license from OOMOL. Releases up to and including v1.9.4 remain under the unmodified Apache License 2.0. See NOTICE.md.

The license for this repository does not grant rights to third-party products, providers, apps, APIs, trademarks, service marks, trade names, logos, icons, brand assets, documentation, screenshots, or other copyrighted materials owned by their respective holders.

Provider and app names, metadata, links, scopes, permissions, and optional logos/icons are included only to identify services and enable interoperability. All third-party brand and product rights remain with their respective owners. Inclusion in this catalog does not imply endorsement, sponsorship, partnership, certification, or verification by those owners.

If you contribute provider metadata or assets, only submit material you have the right to submit. Prefer linking to official public assets instead of copying brand files into this repository.

Please keep issues and pull requests focused, respectful, and actionable. Participation in this project is governed by CODE_OF_CONDUCT.md.

If OpenConnector is useful to you, giving it a ⭐ helps more developers discover the project.

Thanks to everyone who has helped build OpenConnector. Want to join them? See CONTRIBUTING.md.