pickfit

BrowseLocal AI tools

JevAlt

Three 4B models choose between options and return probabilities, running locally via Jev API.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: python>=3.11
  • A GPU is optional
  • At least 3 GB of RAM
  1. install jevalt[serve] from git (gguf extra fails without gcc)

    pip install "jevalt[serve] @ git+https://github.com/mertkayacs/jevalt"

Check that it works

jevalt --help

The output should contain “usage: jevalt”.

First thing to try

cat > /tmp/check_f1.py << 'PY'
from jevalt.engine import DecisionEngine
class DummyBackend:
    name="dummy"
    def count_tokens(self,t): return len(t.split())
    def field_logits(self,text,compiled): return [[5.0 - i*2 for i,_ in enumerate(f.symbols)] for f in compiled.fields]
    def continue_reasoning(self,prefix,max_tokens): return "trace"
b=DummyBackend()
e=DecisionEngine(b, model="dummy")
payload={"state":"I was charged twice for March. Please refund the duplicate.","questions":{"team":{"type":"choice","instructions":"Which team should handle this ticket?","criteria":{"billing":"payments, refunds","technical":"bugs, outages","sales":"prices, contracts"}}}}
res=e.predict(payload)
print(res)
assert "probabilities" in res["answers"]["team"] and "choice" in res["answers"]["team"]
print("F1_OK probabilities choice")
PY
python3 /tmp/check_f1.py

What it does

  • Choose between options and get probabilities
    How to use it
    1. In Python, create a DecisionEngine from jevalt.engine with a backend and model name.
    2. Call predict with a state text and a questions entry of type choice, with instructions and criteria for each option.
    3. Read choice and probabilities under answers in the result.
    Tested
  • Get calibrated probabilities for each question type
    How to use it
    1. In the questions passed to predict, set type to choice, score or noul.
    2. For score, give criteria as a list of levels. For noul, give a single criterion.
    3. Read the probabilities, score or noul value for each question under answers.
    Tested
  • Get an unknown option with reasoning traces
    How to use it
    1. Add "abstain": True and "reasoning": "on" to the request passed to predict.
    2. Read unknown and reasoning for each question under answers in the result.
    Tested

How far pickfit got

Linux x86_64

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

Good for

  • route support tickets to the handling team
  • check inputs against a written policy
  • classify incident severity

An alternative to Kev-4B and Laya.

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 1 Nov 2026
  • Version 0.1.0

Differences the test machine hit

  • README: pip install "jevalt[serve,gguf] @ git+https://github.com/mertkayacs/jevalt"
    In the test: pip install "jevalt[serve] @ git+..."; llama-cpp-python wheel fails to build: CMake Error Could not find compiler gcc, no binary wheel available for this platform

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.