Parametric cad modeling with Javascript

javascript for 🐜's, a tiny runtime with big ambitions

A 3D raycasting engine running inside a TrueType font's hinting virtual machine

Hold-to-talk speech-to-text for macOS. 100% local, powered by WhisperKit and local LLM cleanup. Hold Control to record, release to transcribe and paste.

A minimal email TUI where you read with Markdown and write in Neovim.

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.

Gemma Gem runs Google's Gemma 4 model entirely on-device via WebGPU — no API keys, no cloud, no data leaving your machine.

A ~9M parameter LLM that talks like a small fish.

Apple Intelligence from the command line. On-device LLM via FoundationModels framework. No API keys, no cloud, no dependencies.

Lightpanda: the headless browser designed for AI and automation

A browser designed for agent

AI-generated 3D-printable pegboard toy from a hand-drawn sketch

Semantic analysis

Use LLMs to robustly extract web data

Light, fluffy, and always free - AWS Local Emulator

The open source coding agent.

A minimum viable terminal emulator built on top of the libghostty C API. Ex minimo, infinita nascuntur. 👻🐣

Multi-agent Claude Code manager — run multiple Claude CLI sessions from a single Electron app

Cockpit is a web-based graphical interface for servers.

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

🤗 smolagents: a barebones library for agents that think in code.

Free OpenAI API access with your ChatGPT account.

Official inference framework for 1-bit LLMs

A compiled programming language with Korean keywords, written in Rust

Staggeringly powerful macOS desktop automation with Lua

Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

Turn any MCP, OpenAPI, or GraphQL server into a CLI — at runtime, with zero codegen