AI 开源项目榜。
The all-in-one AI agent. Build mobile apps, frontend, backend, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels. Zero Telemetry.
A deep learning framework for molecular docking
[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.
Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, and other Markdown-capable agents.
Browser automation clicks buttons. OpenTabs calls APIs.
:robot: A collection of awesome things about ChatOps – managing operations through a chat
MLX Studio - Easiest way to run LLM's on your Mac. All in one engine.
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
A comprehensive guide to adversarial testing and security evaluation of AI systems, helping organizations identify vulnerabilities before attackers exploit them.
Ai safety research showing a working bypass to Google's synthid on Nano Banana Pro
Make Azure natural TTS voices accessible to any SAPI 5-compatible application.
Seedance 2.0 × Higgsfield 技能集 | 15 Claude prompt skills for AI video generation — cinematic, 3D CGI, anime, e-commerce ads, music videos & more. Each skill: 2-second hook framework, camera encyclopedia, 5+ production prompts. 含2秒钩子框架、摄像机百科、行业最佳实践提示词工程
Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.
Research archive of Claude Code source and runtime artifacts reconstructed from published npm source maps.
Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.
Forward deployed engineering skills for AI coding agents.
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP, GDPR, HIPAA, NIST CSF, PCI DSS, EU AI Act, ISO 42001, ISO 27701, DORA, CSRD, India's DPDPA, CMMC 2.0, NIST AI Risk, SWIFT, CCPA/CPRA, and others. Benchmark 89% (with skills) vs 55% (without skills). Updated Monthly.
Can Language Models Rebuild Programs From Scratch?
oneapi-pro is an enterprise-grade AI API Gateway built on oneapi（one-api）. It has undergone a full architectural redesign, adding support for subscription plans, active-active clusters, precise billing. 本项目与new-api | sub2api不同之处是oneapi-pro是面向企业AI网关的应用场景，并不适用于中转站
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
Official implementation of HARL algorithms based on PyTorch.
她不一样 恋情分析室 — 微信聊天记录恋爱分析 Agent Skill （曾用名：她爱我吗？）
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.
AndroidWorld is an environment and benchmark for autonomous agents
Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.
Transform your 3D texturing workflow with the power of generative AI, directly within Blender!
China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy.
CS2 一站式创作套件：Demo 库与分析（高光/下饭/仿实战POV/2D 回放/热力图/饰品换肤），OBS 自动录制成片，合辑工作台 + LiteCut 多轨精剪，可选 LLM 毒舌锐评。0 注入、0 Hook、0 逆向游戏进程，本地回放低风险。
AI 算命，占卜，塔罗牌，姓名五格，周公解梦，生辰八字，梅花易数
Official Project Page for Recurrent Looped Transformer (RLT) (https://arxiv.org/abs/2610.07591)