Stars
Use Garry Tan's exact Claude Code setup: 15 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Benchmarking Audio-Visual Social Interactivity in Omni Models
A context and memory system for AI coding agents. Persistent memory, personal rules, skills, and scheduled observations
Flash Attention implementation that returns both output and attention scores. High-performance, memory-efficient attention with score extraction for analysis and visualization.
The first "code-first" agent framework for seamlessly planning and executing data analytics tasks.
Youtu-Tip: Tap for Intelligence, Keep on Device.
Staggeringly powerful macOS desktop automation with Lua
A construction kit for reinforcement learning environment management.
📥 An inbox UX for interacting with human-in-the-loop agents.
MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
A simple yet powerful agent framework that delivers with open-source models
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A lightweight LMM-based Document Parsing Model
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
Model Context Protocol Servers
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
The official repo for “WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?“
LEAKED SYSTEM PROMPTS FOR CHATGPT, GEMINI, GROK, CLAUDE, PERPLEXITY, CURSOR, DEVIN, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
OpenMMLab Detection Toolbox and Benchmark
Fully open reproduction of DeepSeek-R1
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, ...)…
Solve Visual Understanding with Reinforced VLMs
No fortress, purely open ground. OpenManus is Coming.
Master programming by recreating your favorite technologies from scratch.