Kimi Python Packages

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

tokenspeed-mla

TokenSpeed is a speed-of-light LLM inference engine.

claude-tap

Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer.

vllm-tpu

A high-throughput and memory-efficient inference and serving engine for LLMs

tokenspeed-smg

TokenSpeed is a speed-of-light LLM inference engine.

vllm-cpu-nightly

A high-throughput and memory-efficient inference and serving engine for LLMs

agent6

A coding agent that jails model commands and uses editable state machines for long-running tasks

illusion-code

AI-powered CLI coding assistant with Claude Code heritage, deep Windows optimization, bilingual UI,comprehensive Markdown rendering.

coding-proxy

A High-Availability, Transparent, and Smart Multi-Vendor Proxy for Claude Code. Support Claude Plans, GitHub Copilot, Google Antigravity, ZAI/GLM, MiniMax, Qwen, Xiaomi, Kimi, Doubao...

kitty-bridge

Universal LLM bridge for AI agents. Use Claude Code with MiniMax, Codex with GLM, or Gemini CLI with OpenRouter — one command, any provider. Works with coding agents, OpenClaw, Hermes, and others.

harnessnovel

长篇网络小说自动化写作 AI Agent，支持Chatgpt、gemini、Deepseek等国内外模型接入，采用拆书 + 仿写的模式，从新世界观、大纲、卷纲设计，到章节片段完善&章纲设计，有效解决 AI 写作中的「前后矛盾」、「容易遗忘」、「缺乏特色」和「AI味重」等问题，支持 百万字量级 连载创作。

kimi-code-usage

Kimi (Moonshot AI) Coding Plan API usage quota tracker — CLI + MCP Server + VSCode Extension

tokenspeed-kernel-amd

TokenSpeed AMD-specific high-performance kernels.

ai-dynamo-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

llm-onesdk

OneSDK is a Python library that provides a unified interface for interacting with various Large Language Model (LLM) providers.

vllm-acc

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-xft

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-musa

vLLM platform plugin for Moore Threads MUSA GPUs

vllm-consul

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-npu

A high-throughput and memory-efficient inference and serving engine for LLMs

nextai-vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

devorch

Multi-provider AI coding assistant CLI with 13+ providers

vllm-hust

A high-throughput and memory-efficient inference and serving engine for LLMs

kimi4free

A way of using Kimi for free; even with login features.