Starred repositories
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…
🚀 Zero Downtime Deployment for Docker Compose
Configuration DSL for Archlinux, similar to /etc/nixos/configuration.nix but uses your normal archlinux tools (pacman, systemd, gnu-utils) and doesn't do weird acrobat with stores and stuff
EmDash is a full-stack TypeScript CMS based on Astro; the spiritual successor to WordPress
High-Quality Voice Cloning TTS for 600+ Languages
Beginner, advanced, expert level Rust training material
Fully automatic censorship removal for language models
Offensive Security Dataset Generator — MCP server for generating high-quality pentesting conversation datasets for LLM fine-tuning
A collection of DESIGN.md files inspired by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.
🔥 The Web Data API for AI - Power AI agents with clean web data
Digler is a tool for forensic disk analysis and file recovery. It's designed to help you unearth lost or deleted data from various disk images and raw devices.
Create code snippets, browse AI prompts, create extension icons and more.
Everything you need to extend Raycast.
OpenShell is the safe, private runtime for autonomous AI agents.
Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.
Capture AI coding tool prompts as standard git trailers in commit messages. Supports Claude Code, Kiro, Gemini, and Codex.
Hundreds of models & providers. One command to find what runs on your hardware.
LLM Council works together to answer your hardest questions
Offline Linux command inference engine that runs on low-resource and edge devices with no GPU, no API, and no internet connection required.
Lightweight, self-contained Linux® server monitoring tool
practice made claude perfect
An agentic skills framework & software development methodology that works.