Source code of extensions in https://github.com/keiyoushi/extensions

Extension repository for Mihon and variants

Manga reader for Android

Automatically Builds Dantotsu Dev Branch

BossMod FFXIV dalamud plugin

Source code of extensions for Komikku / Mihon & forks.

s&box is a modern game engine, built on Valve's Source 2 and the latest .NET technology, it provides a modern intuitive editor for creating games

olcng - fast, simple VPN

Private server research project for a certain discontinued mobile game

Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves

Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…

Безопасно. Быстро. v2RayTun

カクヨム小説ダウンローダー

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

OpenGame: Open Agentic Coding for Games

Edit Banana: A framework for converting statistical formats into editable.

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Cheat Engine. A development environment focused on modding

Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.

Steam Deck Plugin to apply Framegen mods to games by replacing DLSS DLL with FSR3 DLL

Portable AI music generator — full songs with vocals, covers, music videos. One-click install, 100% offline, NVIDIA GPU.

Rust implementation of TurboQuant, PolarQuant, and QJL — zero-overhead vector quantization for semantic search and KV cache compression (ICLR 2026)

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

TurboQuant: Near-optimal KV cache quantization for LLM inference (3-bit keys, 2-bit values) with Triton kernels + vLLM integration

Per-head entropy-based KV cache compression for efficient LLM inference. 2.6x better than uniform strategies at 2x compression.