Agentspan
agentspan.aiDurable execution for AI agents — crash-safe, human-in-the-loop, full observability.
AI Toolsai-agentsdurable-executionpythonopen-sourcehuman-in-the-loopmulti-agentobservability
About
Agentspan is an open-source Python server and SDK that compiles AI agent definitions into durable workflows backed by an industrial-grade orchestration engine. Agents survive process crashes, support human-in-the-loop approvals, and offer full observability across every tool call and LLM request. It integrates with popular frameworks like OpenAI Agents SDK, Google ADK, and LangGraph with minimal code changes.
Problem
AI agents lose execution state and fail silently when processes crash, lack safe human approval flows, and are difficult to observe and debug in production.
For
AI/ML engineers and software developers building production AI agent systems
How it works
Agent definitions are compiled into durable Conductor workflows hosted on a self-hostable server, so execution state persists outside the user's process and resumes automatically after crashes or worker reconnects.
Business model
open-source
Status
launched