pickfit

BrowseDeveloper CLIs

ai-jury

Multi-agent CLI that reviews diffs, PRs or issues via debating agents into one verdict.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.11
  • Keys or accounts: ANTHROPIC_API_KEY, OPENAI_API_KEY
  1. Install ai-jury via uv tool

    uv tool install ai-jury

Check that it works

jury --version

The output should contain “jury 1.28.0”.

First thing to try

jury --mock

Run jury --mock to see a sample review with mock agents.

What it does

  • Review pull requests, diffs or issues
    How to use it
    1. Run jury --mock to see a sample review.
    2. Read the findings, each listed with severity, file, line and the agents that raised it.
    Tested
  • Have agents debate and check each other's findings
    How to use it
    1. Run jury --mock --rounds 2 to add a cross-examination round.
    2. Look for the "Round 2 — cross-examination" section in the output.
    Tested
  • Reach a verdict through a chair or a vote
    How to use it
    1. Run jury --mock --rounds 1 --decision vote to decide by panel vote.
    2. Check the output for the ballot count behind the verdict.
    Tested
  • Stream output live or as a transcript
    How to use it
    1. Run jury --mock --transcript to get the full transcript.
    2. Find the verdict under "Decision — verdict & reasoning".
    Tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 4 of 4 features work
  4. Works offline

Good for

  • review a GitHub PR
  • review a diff file
  • review an issue for completeness and clarity
  • post review verdict back as PR comment
  • reach verdict by panel vote instead of chair

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 1.28.0

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.