HYSEN LABS DIRECTORY

#Large Language Models

Capability tag · curated repositories and deep analysis.

6,244 curated open-source projects
NVlabs

Fast-dLLM

★ 1,116

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

Python147 forks5 min read
jaredrhod

barehands

★ 1,116

Move things on your screen with your bare hands. A webcam-powered, hand-tracked interface for your AI. No headset. No controllers.

HTML256 forks8 min read
helicalinsight

helicalinsight

★ 1,115

Free, open source BI platform with AI conversational analytics (BYO-LLM), pixel-perfect paginated reports, interactive dashboards, SSO, embedding, multi-tenancy & row-level security. Every feature free in Community Edition. Self-hosted, Docker-ready

JavaScript786 forks7 min read
★ 1,114

Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.

Python110 forks6 min read
momozi1996

momo-code

★ 1,112

MOMO CODE — AI coding agent that evolves with you

TypeScript107 forks7 min read
TheAiSingularity

graphrag-local-ollama

★ 1,112

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

Python161 forks6 min read
JayPokale

Chisle

★ 1,111

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

JavaScript71 forks6 min read
codestable

CodeStable

★ 1,111

CodeStable is an AI coding workflow for serious software engineering that keeps a human in the loop. Rather than centering on agent orchestration, it organizes requirements, architecture, features, issues and historical decisions, making development driven by Codex and Claude controllable, traceable, and sustainably evolvable.

Python80 forks10 min read
★ 1,110

Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.

JavaScript133 forks5 min read
prehisle

relay-pulse

★ 1,109

An enterprise-grade availability monitoring system for LLM relay/proxy services, tracking service status in real time with a visualization dashboard.

Go94 forks5 min read
Wenyueh

MinivLLM

★ 1,109

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

Python183 forks6 min read
ludo-technologies

pyscn

★ 1,109

Code quality analysis for Python in the age of AI coding.

Go80 forks8 min read
★ 1,109

Configures the styling for exporting Markdown to docx, controlling paragraph text, heading numbering and other styles; works with Obsidian, Typora, Siyuan and other Markdown note apps, and can be called as a skill by Codex, Claude Code, etc. A template for exporting Markdown to docx (Word) using pandoc.

Lua113 forks8 min read

A comprehensive guide to prompt engineering: papers, lectures, notebooks and resources (automatically and continuously updated).

MDX105 forks6 min read
jonwiggins

optio

★ 1,107

Workflow orchestration for AI coding agent swarms, from task to merged PR.

TypeScript136 forks7 min read
hashgraph-online

hol-guard

★ 1,107

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

Python275 forks8 min read
★ 1,106

azooKey-Desktop is an open-source Japanese input method for macOS, written in Swift and powered by the Zenzai neural kana-kanji converter. It provides live conversion, optional LLM-based “Magic Conversions”, and Tuner-backed personalization for a smooth, desktop typing experience.

Swift99 forks7 min read
★ 1,106

Agent Skills for Marketing — SEO, Social, Influencer & More. 160+ open-source skills for SEO, content, 40+ page types, paid ads, channels, and strategies. Add project context; get tailored, production-ready output. Cursor, Claude Code, OpenClaw — no lock-in.

Unknown151 forks5 min read
bird-bench

BIRD-CRITIC-1

★ 1,105

[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

Python36 forks6 min read
agentscope-ai

OpenJudge

★ 1,104

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

Python108 forks6 min read