Durable Agent Architecture

Structure a long-lived agent service so any part can crash and resume. Decompose it into brain (model plus harness), hands (ephemeral sandbox and tools), and session (a durable event log), each replaceable on its own, with wake/resume semantics and credentials kept out of the execution environment. Use this whenever someone designs a production or long-running agent backend, asks how to make agents crash-recoverable or resumable, worries about losing session state when a container dies, needs to scale agents as a service, or asks where to keep credentials for an agent that runs code. Trigger on "agent infrastructure," "resume an agent after a crash," "agent runs for hours," "where do tokens live," and similar. Not for parallelizing work across agents or coordinating a shared repo; see multi-agent-orchestration and parallel-autonomous-agents.

Hoja-Solutions 9f157ce 2 files · 5.7 KB Updated

File contents

Hoja-Solutions/agent-stdlib/tree/main/skills/durable-agent-architecture commit 9f157ce61e

Frequently asked questions

npx skillmds@latest add hoja-solutions/durable-agent-architecture