AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻譯準備中
Run a fleet of Claude Code agents from one Go binary — spawn, monitor, and tear them down in isolated git worktrees, track per-agent cost, and see how many tokens you're saving. No database, no SaaS.
翻譯準備中
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Run a fleet of coding agents without losing your mind. warden is a single Go
binary (warden, aliased wd) that spawns, monitors, and tears down coding-agent
sessions — each in its own isolated git worktree — while tracking exactly what every agent
costs and how many tokens its lifecycle features keep out of context. It drives multiple
AI CLIs (Claude Code by default — see AI CLIs),
backed by a local daemon and a file-based JSON store: no database, no SaaS, no telemetry.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Run a fleet of coding agents without losing your mind. warden is a single Go
binary (warden, aliased wd) that spawns, monitors, and tears down coding-agent
sessions — each in its own isolated git worktree — while tracking exactly what every agent
costs and how many tokens its lifecycle features keep out of context. It drives multiple
AI CLIs (Claude Code by default — see AI CLIs),
backed by a local daemon and a file-based JSON store: no database, no SaaS, no telemetry.檢視完整 README ↗