Fast-dLLM
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"
Move things on your screen with your bare hands. A webcam-powered, hand-tracked interface for your AI. No headset. No controllers.
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
Skills for Claude Code CLI such as full stack dev Cloudflare, React, Tailwind v4, and AI integrations.
MOMO CODE — AI coding agent that evolves with you
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
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.
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.
Methodology for faithfully cloning any website (static / React / WebGL) — without copying AI-hallucinated code. Real source first.
An enterprise-grade availability monitoring system for LLM relay/proxy services, tracking service status in real time with a visualization dashboard.
Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
Code quality analysis for Python in the age of AI coding.
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.
A comprehensive guide to prompt engineering: papers, lectures, notebooks and resources (automatically and continuously updated).
Workflow orchestration for AI coding agent swarms, from task to merged PR.
Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.
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.
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.
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards