Graph Memory and Lease Isolation: Multi-Agent State Management in Practice

ShanRizvi · x · 2026-07-29

The author shares engineering details of their multi-agent work state management system. It uses a graph memory to anchor code and task context, allowing a newly launched Claude Code session to seamlessly pick up the state of a previously killed session.

Additionally, the system features built-in leases with epoch fencing. When two agents attempt to work on the same task, the stale session receives an explicit 409 conflict error, preventing silent overwrites. Through active dogfooding, the author notes this architecture successfully caught seven install-path bugs that 977 green unit tests had missed.

Related event: MindGraph Adds Persistent Graph Memory for Coding Agents(8 posts)→

Original post →

More from coding & agent

coding & agent channel →