Lists (23)
AGENT-TOOLS
AI Future
BOOK
BOOK&SLIDE
cloudcomputing
datasets
embedded
face recog
FUCKCOOL
🔮 Future ideas
hack
✨ Inspiration
JURIKO Idea
learning
LLM
music
My Research
NVIM
openCV
RAG
sentimen
tools
wav2vec
Stars
基于内核漏洞CVE-2026-43499的本地提权适配，集成嵌入式 KernelSU.CVE-2026-43499+KernelSU越狱模式
Native Shell is a native UI framework for iOS, Android, macOS, Windows, Linux and the web, built in Rust.
Craft Anything: understand how any software works, and craft your own.
Write HTML. Render video. Built for agents.
Mac.apk: Run Android apps natively on Apple Silicon Macs
The Singularity Desktop Environment (meta repository).
Unlocking _everything_ on the CPU with DRAM scrambling
An open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on a Kintex-7 PCIe card.
Wayland-first Hornero desktop shell: bars, launcher, Dashboard, notifications, Control Center and interactions.
Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own
Annotations for the FlyWire dataset.
Arch Linux + Hyprland desktop: a Quickshell shell with a dynamic island, desktop widgets, notes and tasks, and a one-script installer
Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative a…
Notes of the book System Desgin Interview - An Insider's Guide
Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.
tmux-style terminal multiplexer with native remote capability and restorable & shareable sessions
A governed, isolated headless Chromium runtime for coding agents
Implementation of Trading Strategies for Backtesting in MetaTrader 5 (MT5) Using MQL5 Programming Language – Free Open-Source Trading Bots (Expert Advisors) for MT5
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
A novel serving architecture for LoRA models — route, compose, and serve hundreds of LoRA adapters on a single base model.
A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss,…
Autonomous experiment loop extension for pi
Full Transformer into a custom chip. microGPT in RTL, generating names on a Virtex-5 FPGA at ~56k tokens/second.