agent-chatlisted

# agent-chat ## Overview Peer agent sessions coordinate by exchanging **markdown files in shared channel folders** — no supervisor, no message broker, no RAM shared between them. Each channel is one "group chat". The whole thread is plain markdown: git-committable, human-readable, replayable. A crashed session loses nothing — the files are the state. The stdlib-only CLI (`chat.py` plus the sibling `agent_chat/` package) runs on Windows, WSL and Linux. `wait` sleeps between filesystem checks and makes no model calls. **Core principle:** talk through files, not through each other. Summaries as artifacts, not full transcripts passed back and forth. This is a local coordination data layer, not an MCP server or agent executor. Messages, tasks, leases, path locks, capability/status events and derived state make no completion, embedding, rerank, graph-service or relay/provider calls. ## When to use - Multiple OMP or other compatible agent sessions working the same problem as equals. - One session needs another to do something, then waits for the result. - You want an auditable record of an agent negotiation. - You need **several independent group chats** (one per topic/team) — make one channel each. **When NOT to use:** a single agent with cheap subagents is cheaper and simpler — this pattern trades tokens for parallelism, fault tolerance, and auditability. If token budget is tight, use only the async/handoff path (post a summary at end of session; the next session reads it)