Starred repositories
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Codex skill for generating quiet minimal zine-style editorial poster prompts and images.
OpenPet: local desktop pet runtime for AI agents. 本地桌宠运行时，支持宠物导入与 CLI/MCP/HTTP API 控制。
微信收藏可视化 Claude Code Skill — 从加密 DB 到交互式 HTML 报告的端到端管线
macOS: mount any linux-supported filesystem read/write using NFS and a microVM
Community curated list of templates for the nuclei engine to find security vulnerabilities.
Official repo for Textoon: Generating Vivid 2D Cartoon Characters from Text Descriptions
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…
The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
Enable macOS HiDPI and have a native setting.
Awesome speech/audio LLMs, representation learning, and codec models
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Align Anything: Training All-modality Model with Feedback
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
A generative speech model for daily dialogue.
A fast, simple & powerful blog framework, powered by Node.js.