AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Crash-safe task tracking for AI coding agents over MCP: expiring leases, resumable attempts, version-pinned reviews. One Go binary, one SQLite file per project.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
When a coding agent dies mid-task, the task frees itself.
rhizome-mcp gives autonomous coding agents crash-safe task coordination over MCP: claims are renewable expiring leases, in_progress is derived — never stored — and an interrupted attempt hands its checkpoint to whichever session picks the work up next. One static Go binary, one SQLite database per project. No daemon, no accounts, no cloud.
It works with agents from different products at once — Claude Code, Codex, GitHub Copilot, VS Code, and any other MCP-compatible client — giving them one shared, durable view of project work.README 전문 보기 ↗지금 README 전체를 불러올 수 없습니다. 원문 링크에서 읽을 수 있습니다. 아래는 저장된 발췌입니다.
When a coding agent dies mid-task, the task frees itself.
rhizome-mcp gives autonomous coding agents crash-safe task coordination over MCP: claims are renewable expiring leases, in_progress is derived — never stored — and an interrupted attempt hands its checkpoint to whichever session picks the work up next. One static Go binary, one SQLite database per project. No daemon, no accounts, no cloud.
It works with agents from different products at once — Claude Code, Codex, GitHub Copilot, VS Code, and any other MCP-compatible client — giving them one shared, durable view of project work.README 전문 보기 ↗