👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

🌸 A command-line fuzzy finder

💥 Blazing fast terminal file manager written in Rust, based on async I/O.

A terminal workspace with batteries included

🙌 OpenHands: AI-Driven Development

OpenClaw-RL: Train any agent simply by talking

Aho-corasick graph for hotwords and keyword spotting.

RotorQuant: Clifford algebra vector quantization for LLM KV cache compression. 10-19x faster than TurboQuant, 44x fewer parameters.

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.

A curated list of Claude Skills.

From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

AI agents running research on single-GPU nanochat training automatically

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Create web-based user interfaces with Python. The nice way.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

My learning notes for ML SYS.

Train the smallest LM you can that fits in 16MB. Best model wins!

LLM IS AS GOOD AS YOU ARE

A C++17 single-file header-only wrapper for llama.cpp

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Plug-and-play streaming semantic VAD for real-time full-duplex spoken dialogue systems.

🌈Beamer风格的幻灯片模板集。包含了PowerPoint和Keynote两套格式。

Cross-platform VAD & Audio Event Detection toolkit — Python (PyPI) + TypeScript (npm) + C API. DFSMN models ~2MB, 200x real-time. Runs everywhere: native, browser (WASM), Node.js.

An agentic skills framework & software development methodology that works.