Stars
AI agents running research on single-GPU nanochat training automatically
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
tukuaiai / vibe-coding-cn
Forked from EnzeD/vibe-codingVibe Coding 指南 - 涵盖 Prompt 提示词、Skill 技能库、Workflow 工作流的 AI 编程工作站
Valdi is a cross-platform UI framework that delivers native performance without sacrificing developer velocity.
Practice English, one strike, one step forward; 练习英语,一次敲击,一点进步;
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!
Source code for the X Recommendation Algorithm
Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), Gemini (3.1 Pro, 3 Flash, CLI), Grok (4.2, 4), Perplexity, and more. Updated regularly.
Self-hosted game stream host for Moonlight.
A practical Douyin downloader for both single-item and profile batch downloads, with progress display, retries, SQLite deduplication, and browser fallback support. 抖音批量下载工具,去水印,支持视频、图集、合集、音乐(原声)。免费…
🚀 The fast, Pythonic way to build MCP servers and clients.
A utility-first CSS framework for rapid UI development.
Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
OCR, layout analysis, reading order, table recognition in 90+ languages
The all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
Yi-1.5 is an upgraded version of Yi, delivering stronger performance in coding, math, reasoning, and instruction-following capability.
A bash script to check the status of your IP on various geo-restricted services.
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Tools for merging pretrained large language models.
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.