pickfit

BrowseDeveloper CLIs

Frugon

Local tool that prices LLM call logs and recommends cheaper model routing.

Tested on Linux and Windows

Use it

Linux x86_64

You need first

  • Runtimes: python 3.10-3.13
  • Keys or accounts: OPENAI_API_KEY
  1. permanent install via uv tool (same uv package as candidate 1 one-shot; candidate 1 verified first)

    uv tool install frugon && frugon analyze --demo

Check that it works

uvx frugon --version

The output should contain “frugon 0.2.6”.

First thing to try

frugon analyze --demo

Run frugon analyze --demo to see a sample cost analysis on built-in demo data.

Windows x86_64

You need first

  • Runtimes: python 3.10-3.13
  • Keys or accounts: OPENAI_API_KEY
  1. install frugon via uv tool install

    uv tool install frugon

Check that it works

frugon --version

The output should contain “frugon 0.2.6”.

First thing to try

frugon analyze --demo

Run frugon analyze --demo to see a sample cost analysis on built-in demo data.

What it does

  • Analyze LLM call logs for cost
    How to use it
    1. Run frugon analyze --demo to see an analysis of sample call logs.
    2. Read the summary for the number of calls analyzed and the baseline model.
    Tested
  • Get recommendations for cheaper model routing
    How to use it
    1. Run frugon analyze --demo.
    2. Review the report for which calls could go to cheaper models instead of the baseline.
    Tested
  • Sample candidate models to check quality
    Not tested

How far pickfit got

Linux x86_64

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

Windows x86_64

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

macOS: the project says it runs there; pickfit hasn’t tried it.

Good for

  • analyze LLM call logs to estimate savings from switching models
  • recommend which calls to route to cheaper models
  • capture live LLM calls via local proxy to JSONL
  • write shareable cost savings report as HTML or markdown
  • list candidate models available for cost comparison

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 0.2.6

Windows x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.2.6

Differences the test machine hit

  • README: frugon --help interactive display
    In the test: plain frugon --help hangs/timeouts due to rich paging; pipe through Select-Object -First or use frugon --version
  • README: (Windows steps)
    In the test: pickfit ran these steps in PowerShell 7 (pwsh 7.6.9) as a standard user; the built-in Windows PowerShell 5.1 is not verified and does not run `&&`.

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.