Stars
Source code of the paper "V-Droid: Advancing Mobile GUI Agent Through Generative Verifiers"
开源的每日 arXiv / OpenReview 论文推荐与 AI 阅读平台，支持 GitHub Actions 自动更新、GitHub Pages 部署与论文问答。
AndroidWorld is an environment and benchmark for autonomous agents
GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …
Official implementation of "CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs" (NeurIPS 2025).
🚀 通用 AI IDE 账号管理工具：支持 Antigravity / Codex / GitHub Copilot / Windsurf / Kiro / Cursor / Gemini-cli / CodeBuddy，多账号切换、配额监控、自动唤醒与多开实例管理。 🚀 Universal AI IDE account manager for Antigravity / Codex / …
EcoAgent: An Efficient Device–Cloud Collaborative Multi-Agent Framework for Mobile Automation (AAAI 2026)
[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Mobile-Agent: The Powerful GUI Agent Family
A C++ header-only HTTP/HTTPS server and client library
Python tool for converting files and office documents to Markdown.
Self-implemented NN operators for Qualcomm's Hexagon NPU
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
This Repo is the best place for learning MultiThreading in C++ from beginning to Expert
Practical multithreading tutorials. Languages supported: C++, Java, C#, Python, Javascript/Nodejs.
Local AI runtime for training & running small LLMs directly on Apple Neural Engine (ANE). No CoreML. No Metal. Offline, on-device fine-tuning & inference on M-series silicon.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
Production-ready Claude Code configuration with self-improvement loop, multi-language rules, MCP integrations, and custom skills
Hexagon-MLIR is a compiler toolchain for compiling and executing AI kernels and models on Qualcomm Hexagon Neural Processing Units (NPUs).
从 Andrej Karpathy 推荐的 90 顶级技术博客中抓取最新文章，AI 多维评分筛选，生成一份每日精选日报。更多可见公众号：懂点儿AI
High-speed and easy-use LLM serving framework for local deployment