pickfit

BrowseDeveloper CLIs

Jev-Style

Local toolkit to classify text, route requests, and score options with probabilities.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Python 3.10 or newer
  1. Install jev-style torch backend

    pip install -U "jev-style[torch]"

Check that it works

jev-style --version

The output should contain “0.6.2”.

First thing to try

jev-style serve --fake
curl -s http://127.0.0.1:8765/healthz && echo "---MODELS---" && curl -s http://127.0.0.1:8765/v1/models

Start the local server with jev-style serve, then send requests to it from another terminal.

What it does

  • Classify text and get a probability for each option
    How to use it
    1. Start the server with jev-style serve --fake.
    2. Run jev-style decide "<your text>" --url http://127.0.0.1:8765 --choice "<question>::<option1>,<option2>,<option3>".
    3. Read the probability for each option in the probabilities field of the output.
    Tested
  • Route support tickets and requests
    Not tested
  • Review receipts and screenshots from images
    Not tested

How far pickfit got

Linux x86_64

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

Good for

  • route support tickets
  • decide when to call a larger model
  • review receipts or screenshots with image-capable build

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 0.6.2

Differences the test machine hit

  • README: pip install -U jev-style[mlx] as first candidate
    In the test: On Linux x86_64 use pip install "jev-style[torch]"; mlx backend is Apple-silicon only and cannot work here
  • README: jev-style serve downloads 0.8B weights (~1.5GB)
    In the test: jev-style serve --fake for deterministic answers with no 1.5GB weight download; plain serve needs download and RAM beyond 2GB box
  • README: review receipts or screenshots with the image-capable build
    In the test: Fake server reports images:false and rejects assets with 400 images_not_supported; images need 2B v4 torch build

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.