An ESP-IDF based Stack-chan firmware.

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

Portable application framework with DI — Node, Workers, Lambda... anywhere.

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Chaos engineering for Playwright tests

Open-Source Frontier Voice AI

Saizeriya Protocol Implementation of server and client

A backup-first Codex skill for keeping local Codex state fast, clean, and recoverable.

Skills for Real Engineers. Straight from my .claude directory.

The agent that grows with you

A native TypeScript compiler written in Rust. Compiles TypeScript directly to executables using SWC and LLVM.

Self-hosted software for managing artisanal D2C micro-businesses

(Experimental) A Sans I/O, pure C WebRTC implementation for RTOS and embedded systems.

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

mixi2 Application SDK for TypeScript (Unofficial)

Create, develop, and deploy Slack apps from the command-line ✨

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

CloudPebble - Web-based IDE for Pebble development

Review by codex, develop by claude-code

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Have a natural, spoken conversation with AI!

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

A visual novel game engine written in JavaScript (TypeScript) that allows full customization of the UI.

Inference server for MioTTS, a lightweight and fast LLM-based TTS model.

📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.

A runner for node:test, jest, and tape test suites on top of node:test (and any runtime)

A TTS that fits in your CPU (and pocket)

PersonaPlex code.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience