pickfit

BrowseDeveloper CLIs

admina-org/admina

Open framework for governed AI with PII redaction, injection blocking, audit trails and EU AI Act checks.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Python 3.11+
  1. Install admina with proxy extra via pip

    pip install "admina[proxy]"
Where the README and reality differ
  • README: admina forensic verify with no arguments
    What worked: pass --dir DIR or set FORENSIC_BASE_DIR; an empty dir verifies as valid with 0 records
  • README: admina dev
    What worked: run admina init PROJECT first to create admina.yaml, then cd into it before admina dev

Check that it works

admina --version

The output should contain “admina, version 0.15.3”.

First thing to try

admina plugin list

Run admina plugin list to see which plugins are available.

What it does

These come from the README; pickfit didn’t check them one by one.

  • Remove personal data from prompts and responses
    Not tested
  • Block prompt injections at the proxy
    Not tested
  • Track EU AI Act compliance gaps
    Not tested
  • Control MCP agent tool calls
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

Good for

  • redact PII such as email, SSN, IBAN, phone and IP in prompts
  • screen prompt injections at the proxy
  • validate agent tool calls before execution and audit them
  • run EU AI Act gap analysis and risk classification
  • record governance events in SHA-256 hash-chained audit trail

How pickfit tested it

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

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 0.15.3

Differences the test machine hit

  • README: uv add "admina[proxy]" as first install line
    In the test: pip install works directly with no project; uv add needs a pyproject.toml (uv init first)

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.