KodHau: Tribal Knowledge for AI Agents

KodHau：为 AI 智能体注入团队“部落知识”

Your AI agent doesn’t know what your senior engineer knew. 你的 AI 智能体并不了解你资深工程师所掌握的知识。

Before your agent writes a single line of code, KodHau MCP injects the tribal knowledge of YOUR dev team — architecture decisions, constraints, rejected approaches, and review comments that were never documented. 在你的智能体编写任何一行代码之前，KodHau MCP 会注入你开发团队的“部落知识”——包括那些从未被记录在案的架构决策、技术约束、被否决的方案以及代码审查意见。

We tested on dotnet/runtime repo, one of the most complex repos. Cursor alone said “yes, you can delete it.” Cursor with KodHau surfaced 3 PRs explaining exactly why that would break prod. 我们在 dotnet/runtime 仓库（最复杂的代码库之一）上进行了测试。单独使用 Cursor 时，它提示“是的，你可以删除它”；而结合 KodHau 使用时，它找出了 3 个相关的 PR，明确解释了为什么删除该代码会导致生产环境崩溃。

One tool. Runs locally. Your code never leaves your machine. 一个工具，本地运行。你的代码永远不会离开你的机器。

KodHau MCP gives your AI agent the tribal knowledge of your team: PR history, design decisions, and review comments your senior engineers never documented. KodHau MCP 为你的 AI 智能体提供了团队的部落知识：包括 PR 历史记录、设计决策以及资深工程师从未记录过的审查意见。