HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
Pangu-Immortal

MagicWX

★ 863

Android 17 local LLM prototype with Jetpack Compose and ONNX Runtime for offline AI inference experiments.

Kotlin363 forks6 min read
★ 863

In the AI era, why can't everyone be a Principal Investigator?

TypeScript119 forks9 min read
whitecircle

halo

★ 862

Halo is an open-source framework built by White Circle for training large language and multimodal models

Python46 forks5 min read
★ 862

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.

Unknown13 forks6 min read
★ 861

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

JavaScript160 forks7 min read
★ 861

Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

C++94 forks7 min read
★ 860

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).

JavaScript109 forks6 min read
feitangyuan

motion-web

★ 860

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.

HTML62 forks6 min read
★ 860

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.

TypeScript65 forks6 min read
wenyuanw

quick-prompt

★ 860

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 ✨

TypeScript79 forks5 min read
★ 860

Convert AI coding agent sessions (Claude Code, Cursor, Codex, Gemini, OpenCode, Kimi Code, Hermes) into self-contained, embeddable HTML replays

JavaScript69 forks7 min read
gavamedia

deltafin

★ 859

Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

Rust105 forks6 min read
WooooDyy

AgentGym

★ 859

Code and implementations for the ACL 2025 paper "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments" by Zhiheng Xi et al.

Python118 forks5 min read
huangjia2019

rag-in-action

★ 859

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.

Jupyter Notebook332 forks6 min read
netease-youdao

Confucius4-TTS

★ 859

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Python89 forks7 min read
hoophq

hoop

★ 859

One gateway in front of every protocol. Same policy across MCP, LLMs, databases and containers. Wire-level enforcement at under 5ms.

Go68 forks8 min read
Michael-Jetson

Robotics_Tutorial

★ 858

A systematic robotics teaching document covering math fundamentals, advanced C++, planning and control, SLAM and more.

Python93 forks8 min read
★ 858

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.

Markdown31 forks5 min read
★ 858

A collection of ai skills built on Warren Buffett's investing framework.

Unknown209 forks5 min read
IncarnaMind

IncarnaMind

★ 858

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.

TypeScript62 forks7 min read