Agentor 0.1.0 is a prerelease. It runs on Agentor’s own agent engine, with durable runs, structured output, and any OpenAI-compatible provider built in. Install it with
pip install --pre agentor; plain pip install agentor stays on the stable 0.0.x line. See Installation.Quick example
Build an agent, connect tools, and serve it over the A2A protocol in a few lines:GetWeatherTool() reads a free WeatherAPI.com key from WEATHER_API_KEY, and raises if it is not set. Pass one directly with GetWeatherTool(api_key="...").Start in 5 minutes
Quickstart
Install Agentor and run your first working agent in minutes.
Installation
Set up Python, install Agentor, and configure provider credentials.
Explore by topic
Start Here
Install Agentor, run your first agent, and understand the core entry points.
Build Agents
Learn practical agent construction, deployment, tracing, skills, and A2A basics.
Durable Runs
Save every step of a run so another process can finish it after a crash.
Model Providers
Point Agentor at OpenRouter, Groq, Together, vLLM, Ollama, or your own server.
Tool Use & MCP
Implement tool calling and MCP servers, then integrate them into agent workflows.
Concepts
Understand architecture, lifecycle, security boundaries, and communication patterns.
Guides
Follow end-to-end workflows for building, streaming, deploying, and observing agents.
API Reference
Dive into class-level and tool-level API details for implementation precision.
Recommended paths
First-time builder
Start with quickstart, then move to building agents and custom tools.
Production deployer
Focus on deployment, observability, tracing, and long-running reliability patterns.
Platform integrator
Build MCP servers and A2A-connected agents for broader multi-system integration.
