pickfit

BrowseLocal AI tools

Paddock

Rust inference server for open models on NVIDIA and Apple Silicon with APIs and Studio.

Tested on LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 14 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:zip 8.6.0 zip: Critical Parser Differential & Security Control Bypass via Dual-Header Inconsistencies (Zip Cloaking) Leading to Arbitrary File Overwrite & RCE (GHSA-m665-v7pm-7grj, critical, fixed in 9.0.5)
  • npm:dompurify 3.4.14 DOMPurify SAFE_FOR_TEMPLATES bypass: split template expressions survive in attached shadow root content on DOM output modes (GHSA-cg2g-xh64-v4q7, critical, fixed in 3.4.17)
See 8 more

4 more findings not listed here.

Linux x86_64

You need first

  • Runtimes: Rust, current stable, Node and npm
  • System packages: cmake and a C/C++ compiler
  1. Download Linux x86_64 binary release

    mkdir -p ~/paddock-bin /tmp/paddock-dl && curl -fL -o /tmp/paddock-dl/paddock.tar.gz https://github.com/truespar/paddock/releases/download/v0.1.19/paddock-0.1.19-x86_64-linux.tar.gz
  2. Extract portable binaries

    tar -xzf /tmp/paddock-dl/paddock.tar.gz -C ~/paddock-bin
  3. Install paddock and paddock-runner to PATH

    ln -sf ~/paddock-bin/paddock-0.1.19-x86_64-linux/paddock ~/.local/bin/paddock && ln -sf ~/paddock-bin/paddock-0.1.19-x86_64-linux/paddock-runner ~/.local/bin/paddock-runner && paddock --version

Check that it works

ln -sf ~/paddock-bin/paddock-0.1.19-x86_64-linux/paddock ~/.local/bin/paddock && ln -sf ~/paddock-bin/paddock-0.1.19-x86_64-linux/paddock-runner ~/.local/bin/paddock-runner && ls -l ~/.local/bin/paddock* && paddock --version

The output should contain “paddock 0.1.19”.

First thing to try

paddock --port 11500
curl -sk https://127.0.0.1:11500/

Start the server, then open https://127.0.0.1:11500/ in a browser or with curl -sk https://127.0.0.1:11500/ to reach it.

What it does

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

  • Run a local inference server for open models
    Not tested
  • Use OpenAI- and Anthropic-compatible APIs
    Not tested
  • Generate images and edit pictures
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Answers requests
  4. Works offline

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

Good for

  • downloading and managing models
  • comparing models side by side
  • read a page as text with boxes
  • generate pictures from a text prompt
  • transcribe live audio in 40 locales

An alternative to llama.cpp, vLLM and SGLang.

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 0.1.19 (g9aa69660)

Differences the test machine hit

  • README: cargo build --release -p paddock-manager -p paddock-runner
    In the test: Used prebuilt paddock-0.1.19-x86_64-linux.tar.gz from GitHub releases and symlinked paddock and paddock-runner into ~/.local/bin; box has node/npm only, no rustc/cargo/cmake/gcc and installing a Rust toolchain is forbidden
  • README: AI inference server for NVIDIA GPUs and Apple Silicon
    In the test: Manager runs without GPU and serves Studio at https://127.0.0.1:11500 over TLS with self-signed cert (curl -k needed); log warns 'no usable graphics card ... models cannot run' so no runner inference was attempted
  • README: OpenAI/Anthropic API on the manager port
    In the test: Manager has no /v1/models or /api/health (both return not_found_error) and no /openapi.json; health is Studio HTML at / and status via `paddock ps` because clients talk to runners directly, manager is never a proxy

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.