# oh-my-kimi — Evidence-gated Agent Runtime for Kimi

> oh-my-kimi (OMK) is a CLI runtime that adds evidence gates and worktree isolation to Kimi Code; verified 69★ and ships `omk init/doctor/chat`.

## Install

Copy the content below into your project:

## Quick Use

```bash
npm install -g @oh-my-kimi/cli
omk init
omk doctor
omk chat
```

## Intro

oh-my-kimi (OMK) is a CLI runtime that adds evidence gates and worktree isolation to Kimi Code; verified 69★ and ships `omk init/doctor/chat`.

**Best for:** Kimi Code users who want bounded, inspectable agent runs with verification artifacts

**Works with:** Node.js 20+ and Kimi Code CLI (README positioning as Kimi-native control plane)

**Setup time:** 6-15 minutes

### Key facts (verified)

- GitHub: 69 stars · 6 forks · pushed 2026-05-13.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `omk chat`.

## Main

- Use evidence gates to stop “done by narration”: require a diff, a passing command, or a file existence check before accepting completion.

- Run parallel work in worktrees to avoid context corruption; merge only after you inspect evidence and summaries.

- Treat `.omk/` as your run ledger: keep it in your workflow so runs are replayable, auditable, and shareable when you debug reliability.

### Source-backed notes

- README presents OMK as a Kimi-native control plane with DAG-based execution, evidence-gated completion, and worktree isolation.
- README quickstart shows `npm install -g @oh-my-kimi/cli` then `omk init`, `omk doctor`, `omk chat`.
- README references verification commands like `omk verify --json` and operator UIs like `omk cockpit`/`omk hud` for visibility.

### FAQ

- **Is OMK a prompt pack?**: No — README explicitly says it’s a runtime/control plane, not a prompt pack.
- **Do I need to learn DAGs to start?**: No — start with `omk chat`; use DAG/parallel features once you trust the basics.
- **What’s the minimal verification loop?**: Run `omk doctor`, execute a small task, then check `omk verify --json` before calling it done.

## Source & Thanks

> Source: https://github.com/dmae97/oh-my-kimi
> License: MIT
> GitHub stars: 69 · forks: 6

---

<!-- ZH -->

## Quick Use

```bash
npm install -g @oh-my-kimi/cli
omk init
omk doctor
omk chat
```

## Intro

oh-my-kimi（OMK）是面向 Kimi Code 的 CLI 运行时：加入证据门禁、DAG 执行与 worktree 隔离；已验证 69★，并提供 `omk init/doctor/chat`。

**Best for:** 希望把 agent 运行变成“可验证、可检查、可回放”的 Kimi Code 用户

**Works with:** Node.js 20+ 与 Kimi Code CLI（README 将其定位为 Kimi 原生控制平面）

**Setup time:** 6-15 minutes

### Key facts (verified)

- GitHub：69 stars · 6 forks；最近更新 2026-05-13。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口命令：`omk chat`。

## Main

- 用证据门禁对抗“口头完成”：在接受完成前要求 diff、通过的命令，或文件存在性等证据。

- 并行任务放到 worktree 里，避免上下文互相污染；在核对证据与总结后再合并。

- 把 `.omk/` 当作运行账本：让每次 run 可回放、可审计、可分享，方便你调试稳定性。

### Source-backed notes

- README 将 OMK 定位为 Kimi 原生控制平面：支持 DAG 执行、证据门禁与 worktree 隔离。
- README 的 quickstart：`npm install -g @oh-my-kimi/cli`，然后 `omk init`、`omk doctor`、`omk chat`。
- README 提到验证与可视化：如 `omk verify --json`，以及 `omk cockpit`/`omk hud` 提供运行可见性。

### FAQ

- **OMK 是提示词包吗？**：不是。README 明确说明它是运行时/控制平面，而非提示词包。
- **开始就要学 DAG 吗？**：不需要。先用 `omk chat` 跑通；基础稳定后再用 DAG/并行能力。
- **最小验证闭环是什么？**：先跑 `omk doctor`，做一个小任务，再用 `omk verify --json` 核对证据后再结束。

## Source & Thanks

> Source: https://github.com/dmae97/oh-my-kimi
> License: MIT
> GitHub stars: 69 · forks: 6


---
Source: https://tokrepo.com/en/workflows/oh-my-kimi-evidence-gated-agent-runtime-for-kimi
Author: Skill Factory