Stars
LEAKED SYSTEM PROMPTS FOR CHATGPT, CLAUDE, GEMINI, GROK, PERPLEXITY, CURSOR, LOVABLE, REPLIT, AND MORE! - AI SYSTEMS TRANSPARENCY FOR ALL! 👐
Warp is an agentic development environment, born out of the terminal.
Lightweight coding agent that runs in your terminal
Cursor plugin specification and official plugins
[CVPR 2026] Official Implementation of "Repurposing 3D Generative Model for Autoregressive Layout Generation"
A reusable SOP repository for AI-assisted engineering, with plan-first workflow, task specs, validation strategy, fact write-back, and reusable skills.
Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
💖🧸 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…
Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.
YouTube Transcript Plus is an advanced Node.js package designed to fetch and process YouTube video transcripts (captions).
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
哔哔君 - 哔哩哔哩字幕列表浏览器扩展，功能包括点击跳转，下载字幕，总结字幕，翻译字幕等。
Obsidian Web Clipper templates for various sites.
Get the main content of any page as Markdown.
AI chat assistant for Obsidian with contextual awareness, smart writing assistance, and one-click edits. Features vault-aware conversations, semantic search, and local model support.
LLM Frontend for Power Users.
Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas
提供多款 Shadowrocket 规则，拥有强劲的广告过滤功能。每日 8 时重新构建规则。
Text-audio foundation model from Boson AI
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Train transformer language models with reinforcement learning.
Minimal reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
A Delaunay/Voronoi library for Unity, and a simple destruction effect