Kimi CLI is your next CLI agent.

🆕 Benchmarking Goal-Oriented Software Engineering

The best ChatGPT that $100 can buy.

The AI coding agent built for the terminal.

MiMo-Audio: Audio Language Models are Few-Shot Learners

Sampling profiler for Python programs

slime is an LLM post-training framework for RL Scaling.

OpenAI Frontier Evals

Flexible Python configuration system. The last one you will ever need.

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A toolkit for developing and comparing reinforcement learning algorithms.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

A tool that facilitates building OCI images.

Powerful menu bar manager for macOS

This repo contains the Hugging Face Deep Reinforcement Learning Course.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

AnyCrawl 🚀: A Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts structured SERP results from Google/Bing/Baidu/etc. Native multi-threading for bulk processing.

Zenith - sort of like top or htop but with zoom-able charts, CPU, GPU, network, and disk usage

Open Source DeepWiki: AI-Powered Wiki Generator for GitHub/Gitlab/Bitbucket Repositories. Join the discord: https://discord.gg/gMwThUMeme

Official Python client library for kubernetes

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >70% on SWE-bench verified!

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Turn any webpage/Vue/React and so on into desktop and mobile app under 5M with easy in few minutes. 轻松将任意网站/Vue/React等项目构建为轻量级(小于5M)多端桌面应用和手机应用仅需几分钟. https://ppofficial.netlify.app

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Code and Data for Tau-Bench

Kimi K2 is the large language model series developed by Moonshot AI team

A comprehensive code domain benchmark review of LLM researches.