Run eight agents and answer them from the train

Vendetta lists every agent across your projects by what it needs. The ones that wait for you reach your phone.

How it goes

  1. Open the chooser

    vendetta tui, or a key you bind to it such as Alt s, shows every project with how many agents wait, work, and are ready.

  2. See who's waiting

    The overview puts the agents that need you in the first lane.

    The overview on a phone, on its Needs you tab: an approval and a question, each answered with the buttons on its card
  3. Answer on your phone

    The question is a card with buttons. Your answer goes to that exact process.

  4. Approve the command

    Read what Claude wants to run and why, then Allow once or Deny.

  5. Read the diff

    Committed work shows as a change. Mark a line and the agent gets your comment.

    An agent's change on a phone: the files it touched and the diff of one of them, with a button on each line to mark it
  6. Restore yesterday's conversation

    Ended conversations stay listed. Enter brings back the exact one.

    History on a phone: ended conversations stay listed under the chats, each one a tap away from being restored
  7. Schedule the nightly check

    A schedule sends the prompt every night and records each run. A failed run stops until you look.

    A schedule on a phone: the smoke test failed this morning and stays paused until it is acknowledged, above its timing and the agent it prompts

What it needs

A computer that stays onLinux or macOS
The agents you already useClaude Code, Codex, omp, OpenCode, Gemini CLI, Aider
A phoneThe iPhone app on TestFlight, or any browser

Install it and open the chooser

$ git clone https://github.com/vendetta-sh/vendetta.git
$ cd vendetta && bash install.sh
$ vendetta notify start
$ vendetta tui