kdlbs/kandev：README 來源編輯指南

kdlbs/kandev 的 README 將專案描述為「AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.」。本文只整理倉庫可直接核對的內容，不把 star、Fork 或宣傳語當成品質證明。README 在「Kandev」下寫到：Manage and run tasks in parallel. Orchestrate agents. Review changes. Ship value.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Vision」與相關條目，可以先判斷它是否處理你的實際問題：Your workflow - Every team is different, and not every developer uses AI the same way. Define workflows once, share them across the team, and give everyone a consistent process for working with agents - regardless of experience level.。若需求不同，不應只因專案熱度就採用。本文保留原始專案名、命令與元件名，方便回到一手來源核對。 README 另外列出一項可核對的資訊：Review-first - Humans support production systems. We need to understand (yet) and trust the code that gets deployed.。這類原文條目可用來設計試跑步驟，但不能取代實際環境測試。

README 將運作方式分散在「What」等段落。可確認的線索包括：Organize work across kanban and pipeline views with opinionated workflows and execute multiple tasks in parallel. Assign agents from any provider, and review their output in an integrated workspace - file editor, file tree, terminal,。本文不把未寫出的架構、效能或安全邊界補成結論；真正的執行鏈仍要配合目錄、設定檔與版本標籤檢查。

第一次安裝應從 README 指出的入口開始。目前可核對的命令是： brew install kdlbs/kandev/kandev kandev 如果倉庫沒有命令，本文不會自行編造步驟，而是建議先閱讀「What」，確認系統依賴、預設埠與首次初始化。

日常使用取決於專案文件。README 的「What」段落提到：Run it locally or self-host it on your own infrastructure and access it from anywhere via Tailscale or any VPN.。設定檔、環境變數、權限與資料目錄只在來源明確時才會記錄；沒有寫出的預設值，應在測試環境驗證並保留回滾副本。 同一部分也提到：Remote agents - Running multiple agents on a large codebase can quickly saturate a local machine. The goal is a single control plane: offload execution to servers, orchestrate from anywhere, including your phone.。