Ollama
Run open models locally with one command.
Handles downloading, quantizing, and serving open-weight models behind a local API that most AI coding extensions can point at. The simplest on-ramp to running everything on your own machine.
Best for
Offline coding assistance and keeping code off third-party servers.
Watch out for
Local model quality still trails frontier hosted models on hard tasks.
Using this and stuck anyway?
Knowing the tool isn't the same as finishing the project. If yours has stopped moving, we'll take a look at it.
Tell us what's broken