Open Source Firmware for Robotic Vacuum cleaner

Install pnpm and a JavaScript runtime (Node.js, Bun, or Deno) in one GitHub actions step

Document database with no database server. Tiny, LLM-friendly TypeScript API; DB engine runs to completion in each JS request handler; state lives in S3/R2.

An erosion mod for Minecraft

Manage worktrees without managing worktrees.

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Ghostty Blackhole puts a real, ray-traced black hole inside your terminal. It grows as Claude Code's context window fills up, live. A fresh session is a quiet hole in the corner. A full one swallow…

Fast macOS disk analyzer and cleanup CLI in Rust — ncdu / dust / GrandPerspective alternative. Scan, explore, reclaim space safely (Trash-restorable).

Markdown Review Sidecar Format (MRSF) v1.0 - Sidemark

Write HTML. Render video. Built for agents.

TypeScript library for directly changing files on GitHub

A self-hosted, memory-native AI agent framework and cross-platform GUI application.

Accessibility Skills (accessibility-skills): AI skills that plan, review, test, and audit web accessibility (WCAG 2.2) — Accessibility Planner, Critic, Tester, Perspective Audit, and Bug Reporting …

MCP to allow AI to manage Secure Network Overlays built with defined.net

A client-side Minecraft mod that adds various "tweaks" (= usually small-ish individual features)

A Minecraft mod where walking wears away a path.

Apple MLX optimized HRM-Text inference

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Fork of Ollama that enables a ConfusedAgentException, when the LLM generation gets into an unreliable state

You shouldn't ever lose your work if you're using Git

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

3x decode TPS increase On Qwen 3.6 27B @ temp 0.6 | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.

Chrome DevTools for coding agents

#1 Persistent memory for AI coding agents based on real-world benchmarks

A Claude Code skill for designing learning goals during AI-assisted coding

A Claude or Codex skill for deliberate skill development during AI-assisted coding

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

A library for creating typesafe standardized query keys, useful for cache management in @tanstack/query