pickfit

BrowseLocal AI tools

local-jev

Offline CPU engine for fast autonomous agent choice, score, route and noul decisions.

Tested on Linux

Use it

Linux x86_64

  1. cargo install local-jev (crates.io, compiled with box Rust in about 41s; installs ~/.cargo/bin/local-jev)

    cargo install local-jev

Check that it works

local-jev --version

The output should contain “local-jev 2.0.0”.

First thing to try

local-jev benchmark --iterations 1000

What it does

  • Select among options with confidence scores
    Tested
  • Speculative tool-call proxy for coding agents
    Tested
  • Batch evaluation of decision queries
    Tested
  • Export Prometheus metrics
    Tested

How far pickfit got

Linux x86_64

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

Good for

  • select a choice from options via decision endpoint
  • evaluate batches of decision queries concurrently
  • intercept coding agent tool calls locally
  • run latency benchmark

An alternative to TypeSafe Jev System One.

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 16 Nov 2026
  • Version local-jev 2.0.0

Differences the test machine hit

  • README: cargo install local-jev (Quickstart) and cargo test shows 23 passing tests
    In the test: cargo install local-jev worked with no extra steps; the README's cargo test was not run here.
  • README: p50 Latency 1.0µs; Throughput 1,000,000+ decisions/second
    In the test: The benchmark on this box printed p50 0.00µs and 'inf decisions/sec' (timer resolution); the README's measured figures were not reproduced and were not judged.
  • README: Rust: 1.80+
    In the test: Box has Rust 1.100.0; not tested on older toolchains.
  • README: Choice response example shows logits 5.5/1.2/1.1 and confidence 0.984
    In the test: Real output gave logits 0.9/0.13/0.0 and confidence 0.999; the example numbers are illustrative, the same choice was picked.

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.