Tech stack
5 projects use C++.
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.
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.
Remote desktop you can point at your own relay server
RustDesk is remote desktop software where the relay server is a binary you can run yourself. That is the whole argument: the same convenience as the commercial tools, without your screen sessions transiting a vendor's infrastructure.
Free 2D and 3D game engine with no royalties
Godot ships a complete engine, editor, and export pipeline under the MIT licence, which means no royalties, no revenue thresholds, and no licensing conversation before a project starts.
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.