Skip to content

Agents Gateway

A FastAPI extension for building API-first AI agent services.

Define agents, tools, and skills as markdown files, then serve them as a production-ready API with authentication, persistence, scheduling, notifications, and more.

Why Agent Gateway?

Building AI agent services requires significant boilerplate: API endpoints, authentication, persistence, monitoring, scheduling, and more. Agent Gateway handles all of this so you can focus on defining your agents.

  • Markdown-first — Define agents, tools, and skills as markdown files with YAML frontmatter. No complex framework to learn.
  • Production-ready — Built-in auth, persistence, telemetry, rate limiting, and error handling.
  • Multi-LLM — Use any model supported by LiteLLM (OpenAI, Gemini, Anthropic, Ollama, and more).
  • Extensible — Plug in custom auth providers, persistence backends, notification channels, and context retrievers.

Quick Start

pip install agents-gateway[all]
agents-gateway init myproject
cd myproject
agents-gateway serve

Your agent API is now running at http://localhost:8000 with interactive docs at /docs.

Features

Feature Description
Agents Define agents as markdown files with YAML frontmatter
Tools File-based or code-based tools with automatic schema inference
MCP Servers Connect to external MCP servers for tool discovery
Skills Composable workflows with sequential and parallel steps
Authentication API key and OAuth2/JWT auth out of the box
Persistence SQLite or PostgreSQL with Alembic migrations
Dashboard Web dashboard for monitoring agents, executions, and conversations
Scheduling Cron-based agent scheduling
Notifications Slack and webhook notifications with per-agent rules
Queue Async execution with Redis or RabbitMQ
Memory Automatic memory extraction and recall
Telemetry OpenTelemetry instrumentation
Structured Output Pydantic model or JSON Schema output validation
Context Retrieval RAG integration via pluggable retrievers
CORS CORS middleware for browser clients
Sub-App Mounting Mount Gateway into an existing FastAPI app with full feature parity
Streaming SSE for real-time chat responses
CLI Project scaffolding, dev server, agent management, output formats

Next Steps