Why it's useful
One install, then one command pulls Qwen, Gemma, DeepSeek, gpt-oss and the rest and runs them locally, with an API other apps and agents can talk to. No account or API bill for local use.
What it needs
A decent graphics card or Apple silicon Mac for the bigger models
Image: Ollama. Ollama belongs to Ollama; we just think it's worth knowing about.
More tools like this
Open source · MIT 130k stars on GitHub
Models
llama.cpp
by ggml-org
The engine most local AI apps use to run open language models on ordinary computers.
Open source · Apache-2.0 9.2k stars on GitHub
Video
FilmCraft
by ArtCraft
A free Premiere Pro-style video editor with a timeline, colour grading and sound.
Open source · Apache-2.0 3.8k stars on GitHub
Productivity
WordCraft
by ArtCraft
A free Microsoft Word-style word processor that reads and writes .docx files.