pi-harness
AGENTS.md12 starsChanged 53 days agoNo licenceView on GitHub
PI Harness 是一个本地优先的 Agent Harness：通过浏览器提供 Codex 风格的交互界面，由运行在用户本机的后端 daemon 执行模型调用、Agent Loop、本地文件操作和 Shell 命令。 完整架构说明见 docs/架构设计.md，当前实现与启动配置见 docs/runtime-setup.md。实现与文档发生冲突时，先更新设计并保持两者一致，不要静默引入另一套架构。 不要在同一职责上重复引入同类库。例如已经使用 TypeBox 时，不再为普通 API DTO 引入 Zod；已经使用 pino 时，不再引入另一套日志框架；已经使用 HeroUI 时，不再混用 shadcn/ui、Flowbite、daisyUI 或 Mantine 作为另一套基础组件库。
- Commits and pushes
In this repository3 other files it gives its agents.
- heroui-pro-design-tasteSkill
- heroui-reactSkill
- pi-harness-web-standardsSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.