Stars
The sourcemap of claude code, the best coding agent of the world
Fast, accurate & comprehensive text measurement & layout
The Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
AI agents running research on single-GPU nanochat training automatically
[TPAMI 2025] Official Code for "SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation"
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
Continuous Thought Machines, because thought takes time and reasoning is a process.
Lightweight coding agent that runs in your terminal
Copilot Chat extension for VS Code
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. #1 coding agent on OpenRouter. 1.5M+ Kilo Coders. 25T+ tokens pr…
Scripts and doc for https://www.dolthub.com/repositories/chenditc/investment_data
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
Qlib-Server is the data server system for Qlib. It enable Qlib to run in online mode. Under online mode, the data will be deployed as a shared data service. The data and their cache will be shared …
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
IntelliJ IDEA & IntelliJ Platform
Kode Agent — Design for post-human workflows. One unit agent for every human & computer task.
Minimalistic 4D-parallelism distributed training framework for education purpose
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
verl: Volcano Engine Reinforcement Learning for LLMs
Roo Code gives you a whole dev team of AI agents in your code editor.
Mirage Persistent Kernel: Compiling LLMs into a MegaKernel