Yechan Do

pi-computer-use. Let Pi control your apps on MacOS & Windows

melone. Memory Engine by Clone

data_io. Data pipeline for HRM-Text pretraining

Cola-DLM. The codebase of Cola DLM

cola_dlm. Reproduce work of https://arxiv.org/abs/2605.06548

Crack-CLI. TypeScript

ai4animationpy. A Python framework for AI-driven character animation using neural networks.

framework. A machine learning library with a TypeScript API and Rust backend. CUDA and WebGPU compatibility. Built to understand how ML frameworks and models work internally.

leopard-gecko. The First Context Engineer That Replaces You.

transformer-vm. Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.

agent-skills. Vercel's official collection of agent skills

autoskills-cli. Public GitHub Releases for the Autoskills CLI

heretic. Fully automatic censorship removal for language models

AngelSlim. Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

x-algorithm. Algorithm powering the For You feed on X

tiny-gpu. A minimal GPU design in Verilog to learn how GPUs work from the ground up

rllm. Democratizing Reinforcement Learning for LLMs

tiny-diffusion. A character-level language diffusion model trained on Tiny Shakespeare

croc. Easily and securely send things from one computer to another :crocodile: :package:

dllm. dLLM: Simple Diffusion Language Modeling

nanochat. The best ChatGPT that $100 can buy.

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

tinker-cookbook. Post-training with Tinker

cheat-engine. Cheat Engine. A development environment focused on modding

nn-zero-to-hero. Neural Networks: Zero to Hero

makemore. An autoregressive character-level language model for making more things

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

E2B. Open-source, secure environment with real-world tools for enterprise-grade agents.

codex. Lightweight coding agent that runs in your terminal

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

HRM. Hierarchical Reasoning Model Official Release

linux. Linux kernel source tree

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

Crux. The State Of The Art, intelligence

system_prompts_leaks. Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

matharena. Evaluation of LLMs on latest math competitions

MiniMax-M1. MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

LiveCodeBench-Pro. Python

macOS-use. Make Mac apps accessible for AI agents

Ice. Powerful menu bar manager for macOS

python-sdk. Enable AI to control your desktop, mobile and HMI devices

PhoneAgent. An AI agent that can get things done across iPhone apps.

cua. Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

firecrawl. The API to search, scrape, and interact with the web at scale. 🔥

notte. Best cloud browser infrastructure and web automation platform for your AI (Coding) agents!

openevolve. Open-source implementation of AlphaEvolve

gallery. A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

UI-TARS. Pioneering Automated GUI Interaction with Native Agents

Agent-S. Agent S: an open agentic framework that uses computers like a human

blast. Open-source VMs-as-a-service

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

iMCP. A macOS app that provides an MCP server to your Messages, Contacts, Reminders and more

grok-prompts. Prompts for our Grok chat assistant and the `@grok` bot on X.

Seed1.5-VL. Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

sports. computer vision and sports

ml-fastvlm. This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

GPU-Guide. Graphics Processing Unit (GPU) Architecture Guide

RealtimeVoiceChat. Have a natural, spoken conversation with AI!

void. TypeScript

system-prompts-and-models-of-ai-tools. FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

BillionMail. BillionMail gives you open-source MailServer, NewsLetter, Email Marketing — fully self-hosted, dev-friendly, and free from monthly fees. Join the discord: https://discord.gg/asfXzBUhZr

hammerspoon. Staggeringly powerful macOS desktop automation with Lua

ultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

dia. A TTS model capable of generating ultra-realistic dialogue in one pass.

multipleWindow3dScene. A quick example of how one can "synchronize" a 3d scene across multiple windows using three.js and localStorage

py2app. py2app is a Python setuptools command which will allow you to make standalone Mac OS X application bundles and plugins from Python scripts.

saas-starter-ko. Get started quickly with Next.js, Postgres, StepPay, and shadcn/ui.

unidisc. UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, and inpainting.

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

puppeteer. JavaScript API for Chrome and Firefox

browser. Lightpanda: the headless browser designed for AI and automation

OpenManus. No fortress, purely open ground. OpenManus is Coming.

DeepEP. DeepEP: an efficient expert-parallel communication library

torchtune. PyTorch native post-training library

trl. Train transformer language models with reinforcement learning.

devops-exercises. Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions

siyuan. A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

HongLabLLM. Jupyter Notebook

p2l. Prompt-to-Leaderboard

animation_gathers_sample. 플러터의 animation 모든 것을 모아놓은 샘플 입니다.

htmx. </> htmx - high power tools for HTML

logocreator. A free + OSS logo generator powered by Flux on Together AI

chainwindcss. Draw your design and get Tailwind CSS code instantly using AI. This example has been created using the tldraw SDK, offering features similar to computer.tldraw.com.

awesome-mcp-servers. A collection of MCP servers.

cloth_simulation. C++

free-programming-books. :books: Freely available programming books

storm. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

SeleniumBase. 📊 APIs for web automation, testing, and bypassing bot-detection.

PDFMathTranslate. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

langflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

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

gym. A toolkit for developing and comparing reinforcement learning algorithms.

pdf.js. PDF Reader in JavaScript

manim-video-generator. This application allows you to generate mathematical animations using natural language descriptions. It uses OpenAI's GPT model to convert your descriptions into Manim code, which is then used to create beautiful mathematical animations.

ShowUI. [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

khoj. Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

TinyTroupe. LLM-powered multiagent persona simulation for imagination enhancement and business insights.

alphafold3. AlphaFold 3 inference pipeline.

OpenHands. 🙌 OpenHands: AI-Driven Development

facefusion. Industry leading face manipulation platform

transformers.js. State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

mindcraft. Minecraft AI with LLMs+Mineflayer

BitNet. Official inference framework for 1-bit LLMs

youtube-dl. Command-line program to download videos from YouTube.com and other video sites

mem0. Universal memory layer for AI Agents

pytube. Lightweight, dependency-free Python library and CLI for downloading YouTube videos, playlists, and captions.

yt-dlp. A feature-rich command-line audio/video downloader

gpt-researcher. An autonomous agent that conducts deep research on any data using any LLM providers

pygwalker. PyGWalker: Turn your dataframe into an interactive UI for visual analysis

fourier. An Interactive Introduction to Fourier Transforms