AgentBaton
An MCP server that passes structured context snapshots between AI coding agents so every new session starts where the last one left off.
AgentBaton solves the "amnesia tax" — the context loss that breaks multi-agent workflows when switching between Claude Code, Cursor, Codex, and Cline. Three MCP tools let you snapshot your session state with baton_pass, retrieve it with baton_receive, and list recent handoffs with list_batons. Ships with a live Supabase backend and a dark-theme dashboard on GitHub Pages — works out of the box at zero cost, and a UC Berkeley study found 79% of multi-agent flows fail at exactly this handoff point.
The build log
Follow the work.
New essays and prototypes, in your feed reader. Email subscriptions are paused while I connect a working delivery service. No email is collected here.
Follow via RSS