I'm working on Agentspan: https://github.com/agentspan-ai/agentspan

It's a durable runtime for AI agents.

The thesis: agents should not just be an LLM loop running inside one Python process. Once agents touch real systems, you need crash recovery, retries, human approval, distributed tool execution, cancellation, observability, and execution history.

Agentspan is basically applying the Conductor OSS execution model to agents. Conductor made long-running distributed workflows durable. Agentspan tries to do the same thing for agent executions: give every run an ID, persist the state, let it survive process death, pause for approval, resume later, and inspect what happened.