The b4 tool used by Linux kernel developers to help manage their patch workflow around contributions to the Linux kernel has been seeing work on a text user interface to help with AI agent assisted code reviews. This weekend it successfully was dog feeding with b4 review TUI reviewing patches on the b4 tool itself.
Konstantin Ryabitsev with the Linux Foundation and lead developer on the b4 tool has been working on the “b4 review tui” for a nice text user interface for kernel developers making use of this utility for managing patches and wanting to opt-in to using AI agents like Claude Code to help with code review. With b4 being the de facto tool of Linux kernel developers, baking in this AI assistance will be an interesting option for kernel developers moving forward to augment their workflows with hopefully saving some time and/or catching some issues not otherwise spotted. This is strictly an optional feature of b4 for those actively wanting the assistance of an AI helper.
Ryabitsev shared overnight that he’s now hit the milestone of the first “actual agent-assisted review” using the new TUI on b4 patches itself. He added, “Lots of refinements still needed, but it’s doing useful things, at least.“
This dog-feeding with b4 review and leveraging Claude Code was done with this patch series. There is also this screencast showing off the AI-assisted b4 review process from the terminal. An interesting addition for those Linux kernel developers already using b4 and wanting to leverage LLMs / AI agents to hopefully help augment their code review process.
Separately, also making progress this week in the Linux kernel developer AI space are the latest AI code review prompt helpers being worked on by Chris Mason at Meta.
