HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
Ataraxy-Labs

weave

★ 1,360

Entity-level git merge driver. Resolves false conflicts git invents when independent agents edit the same file. ~95% reduction vs. line-based merge.

Rust50 forks6 min read
LangChat

langchat

★ 1,359

LangChat is an open-source AI agent application platform developed by the LangChat Team, supporting multiple models, agents, knowledge base RAG, skills, MCP and intelligent data Q&A.

Vue266 forks7 min read
vercel-labs

gemini-chatbot

★ 1,359

Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini

TypeScript496 forks6 min read
★ 1,358

Agent skills for daily paper discovery, critical reviews, and connected research notes. Supports English and Chinese.

Python106 forks7 min read
SimonSchubert

Kai

★ 1,357

OpenClaw alternative in your pocket

Kotlin214 forks7 min read
★ 1,357

Wenyan MCP Server lets AI automatically format Markdown articles and publish them to WeChat Official Accounts.

JavaScript144 forks8 min read
★ 1,356

A collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric

Python396 forks6 min read
xalgorix

xalgorix

★ 1,355

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

Go277 forks7 min read
BytedTsinghua-SIA

CUDA-Agent

★ 1,355

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

Python137 forks6 min read
cloudflare

agents-starter

★ 1,355

A starter kit for building ai agents on Cloudflare

TypeScript302 forks8 min read
★ 1,354

The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)

Shell96 forks6 min read
emonney

QuickApp

★ 1,354

AI-ready reference architecture for Angular / ASP.NET Core projects. A hardened foundation with secure authentication, authorization, role and user management, and consistent patterns designed to be safely extended by AI tools. Stop letting AI hallucinate your auth and DB logic - give it a production-grade foundation to build on.

TypeScript620 forks5 min read
★ 1,354

extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

Python115 forks6 min read
LiveBench

LiveBench

★ 1,354

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Python130 forks6 min read

The Simulink Agentic Toolkit gives your AI agent both the tools and the expertise to work effectively with Simulink and Model-Based Design.

HTML129 forks6 min read
fxy2311-youyou

expression-trainer

★ 1,348

An expression-training system: real-time speech-to-text plus a 27,000-word emotion lexicon and an AI expression analysis report. Runs offline - talk to it and it helps you spot the problems in how you express yourself.

JavaScript238 forks6 min read
★ 1,346

Jev-powered model routing, memory, compaction, skill selection, computer and browser use for Hermes agents (also Claude Code and Codex)

Python129 forks8 min read
lean-dojo

LeanCopilot

★ 1,345

LLMs as Copilots for Theorem Proving in Lean

C++129 forks6 min read
★ 1,345

Tianshu is a harness-engineered terminal coding agent runtime (TUI x GUI) with deep prefix-cache optimization for DeepSeek V4 (97-99% steady-state hit rate measured in long sessions). It moves beyond treating the LLM as a mere "tool", building on a Cognitive Virtual Machine (CVM), a self-awareness layer, and Stigmergy-based decaying memory to make the AI a "development partner" with independent judgment and cognitive safeguards.

TypeScript100 forks7 min read