DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to review an agent's changes and send notes back to it with Herdr Gpui

Mark up an agent's diff line by line and send the notes straight back to that agent.

Who it is forA developer who lets a coding agent edit code in a worktree and wants to review the result before accepting it.

The problemReading an agent's changes in a terminal and then explaining fixes in a separate chat is slow and easy to get wrong.

The outcomeThe agent receives your line-level review notes in the session it is working in and can act on them.

What you need first

  • A Herdr daemon installed on your machine first, since this app is only its client
  • macOS 14.2 Sonoma or newer with Homebrew, or a supported Linux distribution with glibc 2.39 or newer, or Windows with PowerShell
  • For building from source: Rust via rustup, plus the Xcode command-line tools on macOS or the Visual Studio C++ build tools and Windows SDK on Windows

Steps

  1. Open the tab strip's + menu and choose Review Changes.
  2. Switch the review to side by side if you want a two-column diff.
  3. Click any line and leave a note, the way you would on a pull request comment.
  4. Click Send to agent to deliver the notes to that agent.

Prompt for your agent

In the herdr-gpui app, open Review Changes for the worktree that <agent-session-name> is editing, leave one note on a changed line, and click Send to agent. Confirm the agent acknowledges the note in its session.

Caveat. The README shows this flow for agents running inside Herdr sessions, so it only applies to work done through your local Herdr daemon.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page