Stars
Run deepseek4 locally on metal right from within Pi
Static TanStack Start catalog for nature-inspired design systems and generated theme assets.
DeepSeek 4 Flash local inference engine for Metal and CUDA
Skills for Real Engineers. Straight from my .claude directory.
🔖 FavBox is a local-first experimental browser extension that enhances and simplifies bookmark management without cloud storage or third-party services.
NDL古典籍OCR-Liteのアプリケーションのリポジトリ(ソースコードを含む)
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
A real-time 3D digital map of Tokyo's public transport system
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
Garry's Opinionated OpenClaw/Hermes Agent Brain
Keep tabs on your tabs. Turn your "New tabs" page into a mission control, so you can close them easily. Built for people who open too many tabs and never close them.
Nanite-Style Gaussian Splatting Render
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
"Vibe-Trading: Your Personal Trading Agent"
"DeepTutor: Agent-Native Personalized Learning Assistant"
你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
将冰冷的离别化为温暖的 Skill,欢迎加入数字生命1.0!Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
Library for reducing tail latency in RAM reads
Turn any content into a personalized AI podcast. NotebookLM-style, except you control the script, voices, and hosts. Listen in Apple Podcasts, Spotify, or any podcast app.
AI-assisted TradingView chart analysis — connect Claude Code to your TradingView Desktop for personal workflow automation
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration
Fast, accurate & comprehensive text measurement & layout
Local Twitter/X bookmark organizer with AI categorization and mindmap visualization
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.