An agent skill that turns codebases or system descriptions into interactive, shareable HTML/SVG architecture maps.
An opinionated Linux distribution bundling a curated desktop setup with terminal, apps, themes, and a CLI, documented in a manual.
Read-only mirror of the community plugin marketplace for Claude Cowork and Claude Code, listing approved plugins for installation.
Open-source web app that turns a single prompt into full interactive courses, built and steered by a multi-agent workbench.
Official Cursor plugins for developer tools, frameworks, and SaaS products, each packaged as a standalone directory with a manifest.
Prompt library of 500+ reverse-engineered GPT-Image2 cases and 20+ industrial templates that turn prompts into reusable structured assets.
Native desktop app that configures Logitech mice, keyboards, and webcams locally, as an alternative to Logitech Options+.
A coding-assistant skill that forces ADHD-friendly replies: action-first answers, numbered steps, and no filler.
Desktop app for local voice AI workflows: voice cloning and design, video dubbing, dictation, and long-form audio production.
A macOS menu bar app bundling per-app volume control, system monitoring, window management, clipboard history, and other desktop utilities.
A skill for Claude Code and other agent hosts that produces 39 editorial diagram types as self-contained HTML+SVG.
An agent skill that runs a structured six-phase security audit of a codebase with adversarial validation and coverage tracking.
AI-powered CLI code review tool that reads Git diffs or whole files, queries a configurable LLM agent, and returns line-precise comments.
A Python library for Google Research's pretrained time-series foundation model for zero-shot univariate and multivariate forecasting.
From-scratch PyTorch project that trains a tiny ~64M-parameter LLM and teaches the full pipeline from pretraining to RLHF.
Self-hosted service that pools free-tier LLM providers behind one OpenAI-compatible API with routing, failover, and per-key rate tracking.
An agent workspace that runs AI agents on tasks and keeps a complete append-only record of every run event.
LLM-powered knowledge framework for enterprise document understanding, RAG Q&A, agent reasoning, and auto-built wiki knowledge bases.
A curated, security-audited library of packaged skills that extend AI coding agents such as Claude Code, Cursor, and GitHub Copilot.
A native macOS hotkey launcher for fuzzy app search, clipboard history, snippets, window management, and running Raycast extensions.
Self-hosted open-source CRM that runs on your own server and uses AI agents to attend, qualify and sell over WhatsApp.
Self-hostable SEO application with focused workflows plus an MCP server and agent skills that let AI agents use your SEO data.