NangoHQ/nango

Connect your agents & product to 1,000 APIs.

What it solves

Nango solves the complexity of building and maintaining integrations with external APIs. It eliminates the need to manually handle authentication, token refreshing, rate limiting, and scaling, allowing developers to focus on integration logic rather than infrastructure.

How it works

Nango provides three core primitives:

  1. Auth: A managed system that handles OAuth, API keys, and token storage for over 1,000 APIs, which you can embed directly into your app.
  2. Proxy: A service that routes your API requests, automatically injecting credentials, handling retries, and managing rate limits.
  3. Functions: A runtime where you deploy custom TypeScript integration logic. You can write these manually or use Nango's AI builder to generate them from natural language descriptions.

Who it’s for

Nango is designed for developers and teams building products that need to connect with external services, including AI agents, data sync pipelines, and webhooks. It is suitable for those who want production-grade infrastructure that is compatible with any backend language or AI agent SDK.

Highlights

  • Supports 1,000+ pre-built API integrations.
  • AI-generated integration code that remains human-readable and version-controllable.
  • Production-ready infrastructure featuring automatic retries, scaling, and observability.
  • Fully open-source with options for cloud hosting, Bring-Your-Own-Cloud (BYOC), or self-hosting.
  • Compatible with major AI tools and agent frameworks like LangChain and MCP.

Related

  • Project
    elie222/inbox-zero

    Inbox Zero is an open‑source AI email assistant and client that organizes Gmail/Outlook, drafts replies in your style, offers bulk unsubscribe, meeting briefs, and Slack/Telegram control, plus a fast web/desktop UI. Self‑hostable via Docker and a CLI wizard.

  • Project
    simular-ai/Agent-S

    An open-source computer use agent framework that operates a real GUI via mouse, keyboard, and screen to complete natural-language tasks across desktop and web applications.

  • Project
    TencentCloud/CubeSandbox

    A high-performance, secure sandbox service for AI agents that provides hardware-isolated MicroVMs with sub-60ms startup times and E2B SDK compatibility.

  • Project
    NoFxAiOS/nofx

    NOFX is an open‑source, self‑hosted trading terminal that runs crypto‑perpetual bots powered by large language models. A Go runtime enforces strict risk limits before any model‑suggested order reaches one of nine supported exchanges. The web UI shows live positions, model reasoning, and lets users edit prompts, indicators, and leverage. Multiple bots can be compared on a public leaderboard. Install via a one‑line script, Docker, or manual build; supports many LLM providers (OpenAI, Claude, Gemini, etc.) and a proprietary pay‑as‑you‑go model service (Claw402).