MagicWX
Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.
In the AI era, why can't everyone be a Principal Investigator?
Halo is an open-source framework built by White Circle for training large language and multimodal models
A 2026 guide to getting ChatGPT Plus/Pro and Codex membership top-ups via third-party recharge, including how to buy ready-made ChatGPT Plus accounts and a guide to using ChatGPT Codex from within China.
Security note: do not upload files your organization restricts from public release; use a locally or on-prem deployed LLM. A Chinese official-document formatting skill that generates editable DOCX files following GB/T 9704-2012. Companion tool CEB: https://github.com/mizzlelover/CEB
Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp
Config-driven animated architecture diagrams: turn one JSON file into a terminal-style, always-running diagram or a light-theme infographic that moves. Outputs H.264 mp4 or a live web page; also a Claude Code style skill (SKILL.md).
Build motion-first, high-touch creative websites on vanilla Three.js / Canvas 2D / WebGL / CSS. A Claude Agent Skill with real physics and automated verification.
The fastest JavaScript BPE Tokenizer Encoder Decoder for OpenAI's GPT models (gpt-5, gpt-o*, gpt-4o, etc.). Port of OpenAI's tiktoken with additional features.
Quick Prompt ✨ 提示词管理与快捷输入浏览器插件 | Browser extension for prompt management and quick input ✨
Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code, Hermes) into self-contained, embeddable HTML replays
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.
End-to-end RAG system design, evaluation and optimization, from the Geek Time RAG bootcamp. Breaks down RAG into 10 core components and includes 4 hands-on projects covering the full pipeline, focused on adapting RAG to real business needs rather than the other way around.
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
One gateway in front of every protocol. Same policy across MCP, LLMs, databases and containers. Wire-level enforcement at under 5ms.
A systematic robotics teaching document covering math fundamentals, advanced C++, planning and control, SLAM and more.
HERO = Hashing · Edge cases · Rubrics · Overbuild — the four shapes coding agents over-defend in. A paste-in contract that stops them. Works with Claude Code, Codex, Antigravity, Cursor, Copilot, Windsurf, Gemini CLI.
A collection of ai skills built on Warren Buffett's investing framework.
IncarnaMind is a free, open-source desktop app for macOS, Windows and Linux where you write with AI and ask questions about your own documents (PDF, Word, PowerPoint, Excel and more). It can check every sentence and figure in a draft against those documents, whoever wrote it, and every answer cites the exact page it comes from.