Skip to main content

A Python-based orchestrator for Kimi Code CLI

Project description

oh-my-kimi (Python Edition) 🐍

A high-performance, Python-native orchestrator for Kimi Code CLI.

[!TIP] Which edition should I use?

  • 🐍 Python Edition (Current): Recommended. Best for AI researchers, algorithm engineers, and Python-native workflows.
  • 📦 NPM Edition: Best for full-stack developers and Node.js users.

Overview

This is the official Python port of the oh-my-kimi orchestration framework. It provides deep integration with the Python-based kimi-cli ecosystem, enabling multi-agent collaboration, advanced skill management, and automated workflows without the overhead of cross-language bridging.

Why Python Edition?

  • Native Integration: Seamlessly share configurations, context, and environment variables with Kimi-CLI.
  • Python Skills: Write custom agent skills in pure Python (main.py) instead of just Markdown.
  • Modern Performance: Built with Typer, Rich, and libtmux for a fast, beautiful terminal experience.
  • No Node.js Required: Pure Python environment, easy to install via pip or uv.

Core Features

  • Smart Pathing: Unified resolution for ~/.kimi and legacy .codex homes.
  • Instruction Overlay: Dynamic AGENTS.md injection with automated Codebase Map generation.
  • Tmux Orchestration: One-click multi-agent team setup (omk team).
  • Real-time HUD: High-refresh monitoring dashboard via rich.live.
  • MCP Infrastructure: Python-native Model Context Protocol servers for state and memory.

Getting Started

Prerequisites

  • Python 3.10+
  • kimi-cli (Python version)

Installation

# Recommended: Install using uv for speed
uv pip install -e .

# Or using standard pip
pip install -e .

Usage

# Check your environment
omk info

# Launch a multi-agent team
omk team "Refactor this module into cleaner abstractions"

# Single-turn ask with project context
omk ask "How does the plugin system work?"

Comparison

Feature Python Edition (🐍) NPM Edition (📦)
Language Python 3.10+ TypeScript / Rust
Integration Native (import/env) Subprocess / Wrapper
Skill Type Python (.py) & Markdown Markdown (.md)
Best For AI/Data Scientists Full-stack Devs
CLI Framework Typer / Rich Yargs / Inquirer

Documentation

For more guides and a full skill catalog, visit the Official Website.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

oh_my_kimi-0.1.0.tar.gz (12.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

oh_my_kimi-0.1.0-py3-none-any.whl (16.6 kB view details)

Uploaded Python 3

File details

Details for the file oh_my_kimi-0.1.0.tar.gz.

File metadata

  • Download URL: oh_my_kimi-0.1.0.tar.gz
  • Upload date:
  • Size: 12.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for oh_my_kimi-0.1.0.tar.gz
Algorithm Hash digest
SHA256 f1dfc7c2b650c9cc308be6fae09fcf83756d328e9e3e39bbbc2edd3cc9d5bcc9
MD5 bf38a55b260058104594c9417925bfb4
BLAKE2b-256 242027d0934d3c238c7b058e79591b229f2dedc09375f22bca8d0e937ef3f5ec

See more details on using hashes here.

Provenance

The following attestation bundles were made for oh_my_kimi-0.1.0.tar.gz:

Publisher: publish.yml on wang-h/oh-my-kimi-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file oh_my_kimi-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: oh_my_kimi-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 16.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for oh_my_kimi-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3ab380eb6ed6db04f320188c5bbd3995b99d29371685941272c3a40d4b0fa041
MD5 25c450b8f866028bfc27c0b5e242f6aa
BLAKE2b-256 9f1393201f34b2cb659183a09e8a18eb4cf804d9873f6a3f0d2942b7916f3b58

See more details on using hashes here.

Provenance

The following attestation bundles were made for oh_my_kimi-0.1.0-py3-none-any.whl:

Publisher: publish.yml on wang-h/oh-my-kimi-python

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page