Starred repositories
A Call of Duty-quality FPS in Three.js, built from a single prompt.
Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Fe…
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page conte…
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Ongoing research training transformer models at scale
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A Foundation Model for Generalist Gaming Agents
PaoPaoRobot history, hero list, introduction, etc.
Dynamic Parkour System is a FREE plugin for Unity that allows anyone to import any model and have an already working controller with parkour capabilities like in Assassin's Creed games.
Godot Engine – Multi-platform 2D and 3D game engine
A god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous soci…
MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.
a C\C++ library and command-line tools for Diff & Patch between binary files or directories(folder); cross-platform; runs fast; create small delta/differential; support large files and limit memory…
C++ examples for the Vulkan graphics API
slime is an LLM post-training framework for RL Scaling.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
FlashMLA: Efficient Multi-head Latent Attention Kernels
Fully open reproduction of DeepSeek-R1
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
Toolkit for linearizing PDFs for LLM datasets/training
An Open Source Machine Learning Framework for Everyone