Godot Engine

Excalidraw

ExcalidrawOpen

Collaborative whiteboard with a hand-drawn look

Excalidraw's sketchy rendering is not decoration. Diagrams that look provisional invite comment, where a crisp vector diagram signals a decision already made, so it is unusually good at the early part of a design conversation.

llama.cpp

llama.cppAIOpen

Inference engine that runs LLMs on almost any hardware

llama.cpp is the layer most local model tooling is built on. It is a C and C++ inference engine with no Python runtime, aggressive quantisation support, and hand-tuned kernels for a remarkably wide range of hardware.

whisper.cpp

whisper.cppAIOpen

Speech recognition that runs anywhere, with no runtime

whisper.cpp is a C and C++ port of the Whisper speech recognition model with no Python dependency, quantised weights, and hardware acceleration across Apple Silicon, CUDA, and plain CPU.

OpenCode

OpenCodeAIOpen

AI coding agent for terminal, editor, and desktop

OpenCode is a coding agent that runs where you already work rather than in a separate chat window. The same session can be driven from a terminal, an editor extension, or a desktop client, and it keeps context across all three.

Ollama

OllamaAIOpen

Run open language models locally with one command

Ollama reduced local model hosting from an afternoon of CUDA troubleshooting to a single pull command. It handles model download, quantisation selection, GPU offloading, and memory management, and exposes an OpenAI-compatible endpoint on localhost.

Browser Use

Browser UseAIOpen

Let AI agents drive a real browser

Browser Use gives an agent a real browser rather than an HTTP client. It handles the translation between a model's intent and DOM actions, keeps a structured representation of the page in context, and recovers from the usual navigation failures.