Tutorials¶
All hands-on tutorials are maintained in the Agentex Python repository.
Available Tutorials¶
Sync ACP (Simple Agents)¶
Basic agent patterns with simple request-response interactions.
- Hello ACP: Your first agent
- Multiturn: Conversation history and memory
- Streaming: Real-time response streaming
Async ACP - Base (Learning & Development)¶
Stateful workflows with full lifecycle control for development and advanced patterns.
- Hello Async ACP: Three-handler pattern fundamentals
- Multiturn: Stateful conversations
- Streaming: Response streaming in complex workflows
- Tracing: Observability and debugging
- Other SDKs: OpenAI Agents SDK and MCP integration
- Batch Events: Efficient multi-event handling
- Multi-Agent Assembly Line: Multi-agent coordination without Temporal
Async ACP - Temporal (Production)¶
Enterprise-ready patterns with durable execution for production deployments requiring reliability and fault tolerance.
- Hello Temporal: First Temporal workflow
- Agent Chat: LLM chat with tools integration
- State Machine: Complex workflow orchestration
- Custom Activities: Custom activities for external operations
- Agent Chat with Guardrails: Safety and validation for agent conversations
- OpenAI Agents SDK Integration: Production-ready agents with OpenAI SDK + Temporal
- OpenAI Agents SDK: Hello World: Automatic durability for LLM calls
- OpenAI Agents SDK: Tools: Single and multi-activity tool patterns
- OpenAI Agents SDK: Human-in-the-Loop: Human approval workflows
Why Tutorials are on GitHub¶
✅ Runnable code: Clone the repository and run examples immediately
✅ Always up-to-date: Code is tested with each SDK release
✅ Complete projects: Full file structure and dependencies, not just snippets
✅ Community contributions: Submit PRs to improve examples
✅ Version alignment: Tutorial code matches the SDK version you're using