SciSharp/BotSharp：README 來源編輯指南

SciSharp/BotSharp 的 README 將專案描述為「AI Multi-Agent Framework in .NET」。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「Connect LLMs to your existing application focused on your business」下寫到："Conversation as a platform (CaaP) is the future, so it's perfect that we're already offering the whole toolkits to our .NET developers using the BotSharp AI BOT Platform Builder to build a CaaP.。這說明的是專案邊界，不是已完成的生產驗證。

從 README 的「Some Features」與相關條目，可以先判斷它是否處理你的實際問題：Support multiple LLM Planning approaches to handle different tasks from simple to complex.。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：Built-in multi-agents and conversation with state management.。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「Connect LLMs to your existing application focused on your business」等段落。可確認的線索包括：It's written in C# running on .Net Core that is full cross-platform framework, the plug-in and pipeline flow execution design is adopted to completely decouple the plug-ins.。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： PS D:\> git clone https://github.com/dotnetcore/BotSharp PS D:\> cd BotSharp # For Windows PS D:\BotSharp\> dotnet run --project .\src\WebStarter\WebStarter.csproj -p SolutionName=BotSharp # For Linux $ dotnet run --project ./src/WebStarter/WebStarter.csproj -p SolutionName=BotSharp 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「Connect LLMs to your existing application focused on your business」，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「Connect LLMs to your existing application focused on your business」段落提到：BotSharp is in accordance with components principle strictly, decouples every part that is needed in the platform builder. So you can choose different UI/UX, or pick up a different LLM providers.。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：Built-in RAG related interfaces, Memory based vector searching.。