pickfit

BrowseLocal AI tools

Big Blue Fish Desktop Pet

Desktop pet that reads on-screen text with OCR and chats via speech bubbles using a local LLM.

Tested on Linux

Use it

Linux x86_64

You need first

  • A GPU is optional
  1. download Linux .deb from GitHub Releases

    curl -fL -o /tmp/bigbluefish.deb https://github.com/Bai-Cute/big-blue-fish-desktop-pet/releases/download/v1.0.5/BigBlueFish-v1.0.5-Linux-x64.deb
  2. extract deb with dpkg-deb -x into ~/apps/bigbluefish

    rm -rf ~/apps/bigbluefish && mkdir -p ~/apps && dpkg-deb -x /tmp/bigbluefish.deb ~/apps/bigbluefish
  3. create ~/.local/bin/bigbluefish wrapper execing BigBlueFish.Linux

    mkdir -p ~/.local/bin && cat > ~/.local/bin/bigbluefish <<'EOS'
    #!/bin/sh
    exec "$HOME/apps/bigbluefish/opt/bigbluefish/BigBlueFish.Linux" "$@"
    EOS
    chmod +x ~/.local/bin/bigbluefish

Run bigbluefish from a terminal to start the pet on your desktop.

What it does

  • Chat about what is on your screen in speech bubbles
    Not tested
  • Hear weather and tech news from the pet
    Not tested
  • Watch over 100 animated actions and reactions
    Not tested
  • Connect a desktop AI agent through MCP
    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

  • report local weather in a speech bubble
  • browse and explain latest tech news
  • generate a spoken bubble on demand for testing

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
  • Version 1.0.5

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: sudo apt install ./BigBlueFish-v1.0.5-Linux-x64.deb
    In the test: no sudo in box; extract with dpkg-deb -x to ~/apps/bigbluefish and wrap BigBlueFish.Linux in ~/.local/bin
  • README: bigbluefish --help / --version
    In the test: binary always initializes Avalonia X11 and fails XOpenDisplay failed without DISPLAY; must launch via DISPLAY=:99
  • README: depends on ffmpeg, tesseract-ocr etc.
    In the test: box lacks ffmpeg/tesseract; app still launches but OCR features limited

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.