Shadow any website for offline viewing, with the JavaScript stripped out

AI-powered screen memory — captures, analyzes, and lets you search/chat your screen history. Powered by Gemma 4 . 100% local, 100% private.

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

Local CLI that strips disfluencies (um, uh, er, erm, ah, hmm, mhm, mm, uh-huh, etc) from recordings of English speech.

🍺 The Package Manager for Everywhere

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, or other AI agents to query data accurately and with full context of your company

Practical productivity tools for Claude Code, Codex-CLI, and similar CLI coding agents.

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thre…

Project the aircraft passing overhead onto your ceiling in real time, from an RTL-SDR — with a live sky layer (sun, moon, stars, ISS) and where each plane is headed.

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

An Open Source implementation of Notebook LM with more flexibility and features

Harden your package manager configs against supply chain attacks.

A non-exhaustive list of package manager hardening recommendations to help prevent supply chain vulnerability attacks. Includes AGENTS.md files, skills and Github Action to audit and enforce these …

Git worktree-based task manager with integrated terminals for CLI coding agents

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Self-hosted AI workspace.

Minimal Claude Code alternative. Single Python file, zero dependencies, ~250 lines.

Yet another coding agent harness, lightweight and written in go.

Build your own high performance LLM inference engine in C++ and CUDA - a smaller version of vLLM

A privacy-preserving Raspberry Pi home security camera that uses advanced end-to-end encryption.

Using Tailscale with an OrbStack VM on macOS

AdGuard Extra is designed to solve complicated cases when regular ad blocking rules aren't enough.

Ultra-light Harness scaffolding for AI agents, a mini version of claude code

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

This is a mirror of the Strix Halo HomeLab wiki, to browse the wiki click on the link below

LLM inference in C/C++

Windows alt-tab on macOS