Personal AI, On Personal Devices
title: Offline Code Reviewer description: Review a pull request on a transatlantic flight, no internet required
π οΈ Offline Code Reviewer β code review on an airplane
Earlier this month I was on a flight from SFO to FRA β eleven hours, no usable Wi-Fi. I had a teammate's pull request open in VS Code. I asked Jarvis to review it. It read the diff, read the three files the diff touched, read the project's CLAUDE.md for conventions, and produced a review with five comments β two of which caught real bugs.
The review took about 40 seconds on the laptop's built-in GPU. No API call. No "you're offline" error. By the time we landed I'd dropped the comments into GitHub and the PR was merging.
The same setup handles:
- Code review β diff + context files + conventions, structured comments.
- Debugging β paste a traceback, Jarvis reads the stack, opens the relevant files, suggests fixes.
- Test generation β point at a function, get back a
pytestfile with edge cases. - Documentation β generate docstrings that actually match the code, because Jarvis has the file open.
Why it's nice
- It works on a plane. Or a train, or a hotel with bad Wi-Fi, or your couch when Comcast is having a day. Same speed every time.
- It sees your repo, not a sanitized chunk. Cloud coding assistants make you upload a context window. The local one just reads
git statusand the files you're working on. - No "we trained on your code" question. Your code never leaves your laptop. Period.
How I set this up
β Tutorial: Code Companion walks through the ReAct-agent + git/file/shell tool stack this uses end-to-end.
β User Guide: Code Assistant is the focused recipe walkthrough for daily-driver code review.
β OpenAI-compatible server β point your editor's existing AI integration (Cursor, Continue, Cody, Aider) at localhost:8000. They mostly don't know they're not talking to OpenAI.