mco
CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
CLI-first orchestration for AI coding agents: run selected agents and models in parallel, compare raw answers, and coordinate review or implementation workflows.
An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.
An LLM-powered visual website builder platform, an open-source alternative to Lovable.
A general framework for distilling human-created multimodal resources into reusable, executable skills that AI agents can browse, compose, and run, validated across diverse domains including web, PowerPoint, Excel, Blender, CAD, Unreal Engine 5, and REAPER-based music production.
Full-stack shadcn/ui blocks for auth, payments, AI, logos, and more
Editable HTML presentation skill for Codex/Claude Code with drag-resize editing, slide reordering, local save/export, and PPTX-to-web conversion. Shout out to @zarazhangrui
AI 编程工具实战指南 — 66 个 Claude Code 技巧 + 10 款工具最佳实践 + 可复制配置模板 | AI Coding Tools Guide with 66 Claude Code tips
Whispering Tiger - OpenAI's whisper (and other models) with OSC and Websocket support. Allowing live transcription / translation in VRChat and Overlays in most Streaming Applications
[EMNLP'25 findings] An easy-to-use Graph RAG system using hierarchical knowledge.
Ackem: a local-first AI desktop companion. Private data stays local; supports memory, mood and extensions. AGPL-3.0.
SlowMist Agent Security Skill: A comprehensive security review framework for AI agents operating in adversarial environments. Core principle: Every external input is untrusted until verified.
Automated SRC vulnerability-hunting system combining FOFA asset mapping with multiple LLM workers for autonomous discovery, review and intelligence accumulation. Powered by StanleyNull.
Self-hosted web UI for Claude and Codex. Push notifications, file uploads, no accounts, no database. Uses your existing CLI session history.
🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it
[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
VS Code-style sidebar for the herdr: file explorer + git source control in one pane — syntax-highlighted previews, VS Code-style diffs, GitLens-style drawers, AI commit messages
Claude Code skills for Obsidian | Claude Code x Obsidian Lab, 5 weeks live, starts Nov 10
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.