Build AI agents on Catalyst

This section is for developers who build AI agents and MCP servers. It takes you from your first agent to running agents in production: durable execution so an agent survives crashes and restarts, an identity for every agent, and policies that control which tools and services it can call.

You keep your agent framework. Catalyst works with Dapr Agents, LangGraph, CrewAI, Strands, OpenAI Agents, Google ADK, Pydantic AI, and more.

Quickstart: Run a durable agent

Pick your agent framework to open its quickstart.

Dapr Agents

CrewAI

LangGraph

Strands

Microsoft Agent Framework

Spring AI

Google ADK

OpenAI Agents

Pydantic AI

Deep Agents

Claude Agents

HolmesGPT

Mastra

Where to go next

Start here

Install the CLI and run your first durable agent in a few minutes.

Concepts

How agents, MCP, durable execution, and identities fit together.

Build

Guides for each agent framework, for MCP servers, and for enterprise identity.

Run & operate

Manage agents, MCP servers, and token budgets, and observe them in production.

Reference

The MCP server reference and the control plane API.

Learn hands-on

🎓Dapr & AI University · Learn this hands-onDapr Agents: Build LLM-powered intelligent applications with tools and workflowsBuild intelligent agents with custom tool calls, MCP integration, and multi-agent collaboration. Requires an OpenAI API key.Intermediate45 minPythonStart the track →