pickfit

BrowseLocal AI tools

Crow

Local AI agent with tools, MCP, memory, skills, vision and image generation.

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.

  • 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)
See 5 more

Linux x86_64

You need first

  • System packages: gtk3, webkit2gtk-4.1, python-gobject
  • A GPU is optional
  1. download CrowSetup-linux-x64 release binary v4.3.0

    curl -fLO https://github.com/nibor1896/Crow/releases/download/v4.3.0/CrowSetup-linux-x64
  2. make binary executable

    chmod +x CrowSetup-linux-x64

Check that it works

./CrowSetup-linux-x64 --help

The output should contain “CrowSetup [options]”.

Run ./CrowSetup-linux-x64 from the folder where you downloaded it to start the Crow setup.

What it does

  • Generate and edit images
    Not tested
  • Use 31 tools through MCP
    Not tested
  • Keep memory, skills and goals
    Not tested
  • Hand off work to subagents
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Opens to its setup screen
  3. 0 of 4 features work
  4. Works offline

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

Good for

  • generate images with Qwen-Image
  • edit images with Qwen-Image
  • run tool-using agent tasks locally

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

It opens to its first-run screen

  • Replayed from scratch
  • Checked on 1 Nov 2026

When pickfit opened it, its first-run (setup) screen rendered. That shows it installs and starts; pickfit did not use any of its features. The launch passed again with the network off.

Differences the test machine hit

  • README: curl -fLO ... && chmod +x ... && ./CrowSetup-linux-x64 installs in one window
    In the test: installer shows Crow Setup window but headless mode blocks with 'Crow needs an NVIDIA RTX 50 series GPU, and nvidia-smi reports none' without GPU
  • README: needs gtk3, webkit2gtk-4.1, python-gobject
    In the test: libwebkit2gtk-4.1-0 and libgtk-3 present, python3-gi missing caused warn but GUI still launched

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.