pickfit

BrowseDeveloper CLIs

AI Badger

Local-first tool that prepares focused repo context to paste into any AI chat for review.

Tested on Linux

Use it

Linux x86_64

  1. Download install script

    curl -fsSL https://raw.githubusercontent.com/PVRLabs/aibadger/main/install.sh -o /tmp/install.sh
  2. Install badger via script

    sh /tmp/install.sh

Check that it works

badger --help

The output should contain “AIBADGER - local repository context and review bridge”.

First thing to try

mkdir -p /tmp/badger-demo && printf 'def add(a, b):\n    return a + b\n' > /tmp/badger-demo/calc.py && printf '# Demo\nA tiny project for badger smoke test.\n' > /tmp/badger-demo/README.md && printf 'print("hello")\n' > /tmp/badger-demo/main.py && ls -R /tmp/badger-demo && echo SETUP_OK
cd /tmp/badger-demo && git init -q && git add . && git -c user.email=t@t.t -c user.name=t commit -qm init && echo "second line" >> calc.py && git diff --stat && echo GIT_OK
badger map /tmp/badger-demo

Run badger map <repo> in a repository to generate an offline HTML map of the code.

What it does

  • Get a second opinion on code changes
    How to use it
    1. Make your changes in a git repository.
    2. Run badger api review-context --root <repo> --mode default to build a review prompt with your changes.
    3. Paste the output into any AI chat.
    Tested
  • Extract focused repo context for AI chat
    How to use it
    1. Write your goal in a text file, and list the files you want in a selectors file, one per line, such as FILE:<file>.
    2. Run badger api extract --root <repo> --focus code --input <selectors-file> --goal-file <goal-file>.
    3. Paste the output into any AI chat.
    Tested
  • Generate an interactive offline codebase map
    How to use it
    1. Run badger map <repo> to create an HTML report of the codebase.
    2. Open the generated HTML file in a browser.
    Tested
  • Review and apply AI-suggested changes
    Not shown working

How far pickfit got

Linux x86_64

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

Good for

  • get a second opinion on code changes via AI chat
  • generate an offline interactive HTML map of a repository
  • run focused review or design workflows on a repository

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 v0.8.3

Differences the test machine hit

  • README: badger, badger review
    In the test: use stable non-interactive API (badger api review-context / extract / review-continuation) with --root and input files for headless verification; interactive badger / badger review need a TTY with clipboard/browser
  • README: badger map to generate an interactive, offline HTML map
    In the test: badger map /tmp/badger-demo wrote HTML to cwd (/home/sbx/work/badger-codemap-badger-demo.html), not inside the target dir

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.