study8677/repobrain：README 來源編輯指南

study8677/repobrain 的 README 將專案描述為「🧠 RepoBrain (formerly Antigravity) , Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.」。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「Give your repo a brain 🧠 , ChatGPT for your codebase, works in Claude Code, Cursor, Codex, Windsurf & 4 more.」下寫到：> 99% factual · 2.1× faster than Codex CLI · works in any AI IDE. > Head-to-head benchmark ↓ > Codex CLI users , drop the repobrain: prefix; the same four slash commands ship there too.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Key design choices」與相關條目，可以先判斷它是否處理你的實際問題：Smart grouping: Files grouped by import relationships, directory co-location, filename prefixes. Build artifacts filtered. Hard character limit (800K) prevents context overflow.。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：LLM as analyzer: No AST parsing or regex , source code is fed directly to LLMs. Works with any programming language out of the box.。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「Why RepoBrain?」等段落。可確認的線索包括：> An AI Agent's capability ceiling = the quality of context it can read.。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： Traditional approach: RepoBrain approach: CLAUDE.md = 5000 lines of docs Claude Code calls ask_project("how does auth work?") Agent reads it all, forgets most Router → ModuleAgent reads actual source, returns exact answer Hallucination rate stays high Grounded in real code, file paths, and git history 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「Give your repo a brain 🧠 , ChatGPT for your codebase, works in Claude Code, Cursor, Codex, Windsurf & 4 more.」，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「Why RepoBrain?」段落提到：rb-refresh deploys a multi-agent cluster that autonomously reads your code , each module gets its own Agent that generates a knowledge doc. rb-ask routes questions to the right Agent, grounded in real code with file paths and line numbers.。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：No information loss: Large modules produce multiple agent.md files , no merging or compression. Parallel reads + Synthesizer recombines at answer time.。