pickfit

BrowseLocal AI tools

Mica

Mica is a 4B model server that returns calibrated probabilities for yes/no, choice and score questions.

Use it

Before you install: known vulnerabilities

pickfit found 6 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • pypi:torch 2.7.1 An issue in the component torch.linalg.lu of pytorch v2.8.0 allows attackers to cause a Denial of Service (DoS) when performing a slice operation. (PYSEC-2025-203, high, fixed in 2.9.0)
  • pypi:transformers 5.5.0 Hugging Face Transformers downloads custom generation code before trust consent (GHSA-x9r9-c232-4q39, high, no fix yet)
See 4 more

Linux x86_64

You need first

  • Runtimes: Python 3.10 to 3.13
  • A GPU is required
  1. clone Mica repository

    rm -rf Mica && git clone --depth 1 https://github.com/akivet/Mica
  2. install CUDA serving requirements (candidate 1)

    pip install -r Mica/v0.5/serving/requirements.txt
  3. install pytest for README tests

    pip install pytest
Where the README and reality differ
  • README: python -m pytest tests (requirements.txt / v0.5/serving/requirements.txt do not list pytest)
    What worked: pip install pytest before running tests

Check that it works

cd Mica && python -m mica.server --help

The output should contain “--gguf GGUF”.

First thing to try

cd Mica && python -m pytest tests -q

What it does

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

  • Answer yes/no, choice and score questions
    Not tested
  • Get a probability for every answer
    Not tested
  • Flag uncertain cases instead of guessing
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Main function works
  4. Works offline

Good for

  • decide whether a full refund should be approved automatically
  • score how urgent a support ticket is

An alternative to Jev and CoCo Decision.

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

Differences the test machine hit

  • README: python -m mica.server --help
    In the test: run python -m mica.server --help from the cloned Mica/ directory (README clones then cds, examples assume that cwd)

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.