Stars
A highly customizable UI plugin for KOReader that features a home screen, bottom navigation bar, top bar and desktop modules/widgets.
Personal deep learning study notes and tutorial-style notebooks
"QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks"
Ideogram 4: Open image model at the forefront of design
The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with 100+ tok/s single-request decode with support of FP8 weight
PandOCR is a lightweight PaddleOCR-VL 1.6 WebUI that closely recreates the official online demo experience, with easy file upload, preview, OCR parsing, task history, and Markdown/image export.
Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs
The agent that grows with you
Learn it. Build it. Ship it for others.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to...
Book OCR Pipeline → Markdown (PaddleOCR-VL-1.5 + llama-server)
A library of HTML slide templates designed so any coding agent can pick the right one and produce a beautiful deck on the user's behalf, automatically.
Scaling Autonomous Research in Medical Image Segmentation
A collection of agent skills for CAD, robotics and hardware design
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & En...
Open-source, community-driven agent harness
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sa...
a toolkit on knowledge distillation for large language models
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swa...
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
《李宏毅深度学习教程》(李宏毅老师推荐👍,苹果书🍎),PDF下载地址:https://github.com/datawhalechina/leedl-tutorial/releases
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Warp is an agentic development environment, born out of the terminal.
The first autonomous, continuously-running trading agent for prediction markets. Live on Polymarket.