AI Agent Skills

Apache BifroMQ (Incubating) is a high-performance, distributed MQTT broker that natively supports multi-tenancy. It is designed to enable the building of large-scale IoT…

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mix…

Modern and standards-compliant Z-Wave device driver that runs almost anywhere

A complete typescript implementation of the Matter protocol specification (https://buildwithmatter.com). Includes full support for controller, device, commissioning, sec…

Cotabby is local AI autocomplete for your entire Mac. Open source. On device. Everywhere you type.

A lightweight macOS selection translator built with pure Swift 6, featuring on-device Apple Translate for privacy, only 5MB install size and stable ~50MB memory usage. 一…

On-device streaming speech-to-text engine powered by deep learning

Chronicler is a free, offline worldbuilding tool and local wiki for writers, game masters, and tabletop RPG creators. It saves your notes as plain Markdown files on your…

Home Assistant integration for GeekMagic displays (SmallTV Pro/Ultra). Server-side rendering, no device flashing required.

Access your terminal and your AI agent from any device — phone, tablet, desktop.

Open-source, local-first AI journal app for iOS and Android. Capture text, photos, and voice — AI agents organize them into timeline cards and insights. Your data stays…

On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.

SpyGuard is a forked and enhanced version of TinyCheck. SpyGuard's main objective is to detect signs of compromise by monitoring network flows transmitted by a device.

Home Assistant component for TP-Link and Mercusys router administration with sensors, button reboot, switches and device tracking.

PennyWise automatically reads transaction SMS messages and transforms them into organized financial data with on-device AI assistance. No manual entry, no cloud processi…

The retrieval layer for production AI systems. Lightning-fast (<10ms) search without vector databases. Built for browser, edge, on-device, and cloud.