AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
Advisory intention claims and negotiated agreements for autonomous coding agents — the client. Zero dependencies.
저장소 README에서 가져옴
README 전체를 불러오는 중입니다. 아래는 저장된 발췌입니다.
Coordination and negotiation for autonomous software-engineering agents working
in shared repositories. This is the client — the binary you install, the
hooks it writes into your agent, and the wire types both halves agree on. The
registry it talks to is a separate program.
Six engineers each driving a coding agent do not collide because they are
careless. They collide because nobody knows who would care, agents edit wider
than a human would, and the first evidence of an overlap is a merge conflict or
a silently reverted fix.README 전문 보기 ↗지금 README 전체를 불러올 수 없습니다. 원문 링크에서 읽을 수 있습니다. 아래는 저장된 발췌입니다.
Coordination and negotiation for autonomous software-engineering agents working
in shared repositories. This is the client — the binary you install, the
hooks it writes into your agent, and the wire types both halves agree on. The
registry it talks to is a separate program.
Six engineers each driving a coding agent do not collide because they are
careless. They collide because nobody knows who would care, agents edit wider
than a human would, and the first evidence of an overlap is a merge conflict or
a silently reverted fix.README 전문 보기 ↗