Documentation

Agentspan is a durable runtime for AI agents. Your code runs in your process. Execution state lives on the server.

Agentspan is a durable runtime for AI agents — execution state lives server-side, so crashes, restarts, and deployments don't lose work. Write agents natively or wrap an existing LangGraph, OpenAI Agents SDK, or Google ADK agent in one line.

Getting Started

• Why Agentspan — Why agents fail in production, and how Agentspan solves it
• Quickstart — Build your first agent in 5 minutes

Concepts

• Agents — The Agent class, parameters, results, handles
• Tools — @tool, http_tool, mcp_tool, approval_required
• Multi-Agent Strategies — All 8 strategies, the >> operator, nesting
• Guardrails — Input/output safety, retry, block, fix
• Memory — Conversation history, semantic search across sessions
• Streaming — Events, async, HITL with streams
• Testing — mock_run, expect, record/replay, pytest

Deployment

• Deployment overview — Local, Docker, Orkes Cloud

Reference

• CLI Reference — All commands with exact syntax
• LLM Providers — All providers, model strings, API keys