The Unofficial and Awesome Home Assistant MCP Server

26m function call model that runs on incredibly small devices

Qwen3.6-27B AWQ4 + DFlash on AMD Strix Halo: reproducible vLLM setup, launcher, and benchmarks

Proton Mail Bridge application

The sandbox agent framework.

Agent skill that generates rich HTML pages or slide decks for diagrams, diff reviews, plan audits, data tables, and project recaps

Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents

YouTube Music TUI client with vim keybindings, synced lyrics, and cross-platform media keys

A terminal UI for Android developers. Monitor performance, browse logs, query databases, record traces, and control devices — without leaving the terminal.

A TUI application for managing systemd services.

Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖

A polished input surface extension for pi, with a rounded multiline editor and inline model/context/status glance.

Hide the cursor when pi isn't focused

A TUI to find the best Hetzner dedicated server auction deals, with PassMark CPU benchmarks built-in

Flash ZSA keyboards from your terminal.

Harbor is a framework for running agent evaluations and creating and using RL environments.

A minimalist, offline-first markdown note-taking app

Skills for Real Engineers. Straight from my .claude directory.

Terminal Markdown previewer — GUI-like experience.

Replace port numbers with stable, named local URLs. For humans and agents.

PgQue – Zero-bloat Postgres queue built on top of on battle-proven Skype's PgQ. One SQL file to install, pg_cron to tick.

KeyV2: A Parametric Mechanical Keycap Library

Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

The hacker's BLE (bluetooth low energy) browser terminal app

An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.

The operations layer for your local LLM stack

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

AI-powered subdomain enumeration tool with local LLM analysis via Ollama - 100% private, zero API costs

Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface