Cloud-free local control of the OmniBreeze DC2313R Tower Fan with Wi-Fi (sold at Costco) using ESPHome

Google Home mini "jailbreak" for conversational AI agents

Local-first GitHub dashboard for maintainers to triage, review, and merge PRs and issues across repos without needing GitHub's built-in notification emails or dashboard

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

Zig INferenCe Engine — Local LLM inference on AMD GPUs and Apple Silicon

Low Latency inference for sliding window LSTMs

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Tutorials, Guides and Agent Skills Directories

State-of-the-art TTS model under 25MB 😻

Open Source Continuous Inference Benchmarking Qwen3.5, DeepSeek, GPTOSS - GB200 NVL72 vs MI355X vs B200 vs GB300 NVL72 vs H100 & soon™ TPUv6e/v7/Trainium2/3

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

This repo contains CUDA-Q Academic materials, including self-paced Jupyter notebook modules for building and optimizing hybrid quantum-classical algorithms using CUDA-Q.

Staging area for a public release of Theorizer

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.

Neural Networks: Zero to Hero

Walks you through the steps of scrubbing all of your social media accounts to help prevent doxxing and online harassment. (Project of https://activistchecklist.org/)

Instagram Like Remover - Safely bulk unlike Instagram posts with enhanced security, graceful termination, timestamp logging, and intelligent rate limiting. Features 2FA support, session persistence…

AI agents running research on single-GPU nanochat training automatically

Supercharge Your LLM with the Fastest KV Cache Layer

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP technology

Efficient and scalable zero-shot entity linking

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

Set up a developer friendly Arch Linux system in minutes. Also supports WSL 2, Debian, Ubuntu and macOS for CLI tools!

A CLI to estimate inference memory requirements for Hugging Face models, written in Python.

Build effective agents using Model Context Protocol and simple workflow patterns