# Dapr Agents Quickstarts

Build LLM-powered autonomous agentic applications using Dapr Agents and run them with Catalyst. Dapr Agents is a framework for creating AI agents that can execute tasks, make decisions, and collaborate through workflows, while leveraging Dapr's distributed systems capabilities for reliable execution at scale.

Try one of these quickstarts to run a Dapr Agent application with Catalyst.

- [Durable Agent Quickstart](https://docs.diagrid.io/develop/agents/dapr-agents/durable-agent-quickstart) — Run a durable travel assistant agent with conversation memory and state persistence.
- [Multi-Agent Workflow Quickstart](https://docs.diagrid.io/develop/agents/dapr-agents/multi-agent-workflow-quickstart) — Orchestrate triage and expert agents as child workflows in a deterministic customer support flow.
- [Multi-Agent Orchestrator Quickstart](https://docs.diagrid.io/develop/agents/dapr-agents/multi-agent-orchestrator-quickstart) — Run an LLM-driven orchestrator that dynamically delegates to triage and expert agents via pub/sub.

Prefer a guided, hands-on course? Learn Dapr Agents on Dapr & AI University.

**Dapr & AI University — Learn this hands-on:** [Dapr Agents: Build LLM-powered intelligent applications with tools and workflows](https://www.diagrid.io/university/dapr-agents?utm_source=docs&utm_medium=cta&utm_campaign=dapr-agents)

Build intelligent agents with custom tool calls, MCP integration, and multi-agent collaboration. Requires an OpenAI API key.

Intermediate · 45 min · Python

**Dapr & AI University — Learn this hands-on:** [Dapr Agents - Fix Outdated Agent Answers](https://www.diagrid.io/university/dapr-agents-web-context?utm_source=docs&utm_medium=cta&utm_campaign=dapr-agents-web-context)

Give agents live web results with Tavily so they stop answering from stale training data. Requires OpenAI and Tavily API keys.

Intermediate · 30 min · Python