pickfit

BrowseLocal AI tools

Camelid

Rust app for offline chat, file work, and coding with GGUF models via desktop, browser, and terminal.

Tested on macOS and LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 6 known high or critical vulnerabilities (10 findings, one per affected package version) in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:zip 4.6.1 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 9 more

macOS arm64

You need first

  • A GPU is optional
  1. Download DMG from latest release

    curl -fsSL -o /tmp/camelid-desktop-macos-arm64.dmg https://github.com/timtoole02/Camelid/releases/latest/download/camelid-desktop-macos-arm64.dmg
  2. Download SHA256 checksum

    curl -fsSL -o /tmp/camelid-desktop-macos-arm64.dmg.sha256 https://github.com/timtoole02/Camelid/releases/latest/download/camelid-desktop-macos-arm64.dmg.sha256
  3. Mount DMG

    mkdir -p ~/Applications && mkdir -p /tmp/camelid-mount2 && hdiutil attach -nobrowse -mountpoint /tmp/camelid-mount2 /tmp/camelid-desktop-macos-arm64.dmg -quiet
  4. Copy app to ~/Applications and detach

    cp -R /tmp/camelid-mount2/"Camelid Desktop.app" ~/Applications/ && hdiutil detach /tmp/camelid-mount2 -quiet
  5. Clear quarantine and verify codesign

    xattr -cr ~/Applications/"Camelid Desktop.app" && codesign --verify --deep --strict ~/Applications/"Camelid Desktop.app"

Run camelid pull <model> to download a model, then camelid serve --model <model file> to start the local server.

Linux x86_64

You need first

  • A GPU is optional
  1. Download Linux engine archive

    mkdir -p ~/apps/camelid && curl -fL -o /tmp/camelid-linux.tar.gz https://github.com/timtoole02/Camelid/releases/download/v0.8.0/camelid-linux-x86_64.tar.gz
  2. Install camelid engine to PATH

    tar -xzf /tmp/camelid-linux.tar.gz -C /tmp && mkdir -p ~/.local/bin && cp /tmp/camelid-linux-x86_64/camelid ~/.local/bin/camelid && chmod +x ~/.local/bin/camelid && ~/.local/bin/camelid --version

Check that it works

camelid pull

The output should contain “Download one with:”.

First thing to try

camelid pull

Run camelid pull <model> to download a model, then camelid serve --model <model file> to start the local server.

What it does

  • Chat with GGUF models on your own machine
    How to use it
    1. Download a model with camelid pull <model>.
    2. Start the server with camelid serve --model <model file> --no-open --addr <host:port>.
    3. Send a chat request with curl -s http://<host:port>/v1/chat/completions -H "Content-Type: application/json" -d '<your request JSON>'.
    Tested
  • Use an OpenAI-compatible API
    How to use it
    1. Start the server with camelid serve --model <model file> --no-open --addr <host:port>.
    2. Check that the model is ready with curl -fsSL http://<host:port>/v1/health.
    3. Send chat requests to http://<host:port>/v1/chat/completions in the OpenAI format.
    Tested
  • Browse and preview generated files
    Not tested
  • Write code in chat and review edits
    Not tested

How far pickfit got

macOS arm64

  1. Installs
  2. Opens
  3. Not used yet
  4. Works offline

Linux x86_64

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

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

Good for

  • chat with local models with markdown replies
  • preview and download generated files
  • code in a local project with reviewed edits
  • do web research with reply sources
  • search local document library

How pickfit tested it

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

macOS arm64

It opens to its main screen

  • Replayed from scratch
  • Checked on 1 Nov 2026
  • Version 0.8.0

When pickfit opened it, its main 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 -fsSL https://raw.githubusercontent.com/timtoole02/Camelid/main/scripts/get-desktop-macos.sh | bash installs to /Applications
    In the test: Standard user cannot write to /Applications; installed to ~/Applications via manual DMG mount (mkdir -p ~/Applications, hdiutil attach, cp -R, xattr -cr, codesign --verify) using same DMG URL the script uses
  • README: No mention of quarantine handling
    In the test: App is ad-hoc signed not notarized; curl download avoids quarantine but xattr -cr still required to verify and launch cleanly

Linux x86_64

Installs and starts

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version camelid v0.8.0

Differences the test machine hit

  • README: Download desktop app for Windows/macOS/Linux platforms
    In the test: Linux asset camelid-linux-x86_64.tar.gz contains only headless camelid engine + CUDA libs; no desktop window app for Linux (desktop bundles are Windows zip/exe and macOS DMG only)
  • README: camelid serve --model models/Llama-3.2-3B-Instruct-Q8_0.gguf and chat model Llama 3.2 3B Instruct
    In the test: used catalog tiny model gemma3_270m_it_q8_0 (278 MB, models/gemma-3-270m-it-Q8_0.gguf) and model id Gemma-3-270M-It from /v1/health
  • README: Read loaded model ID from GET /v1/models
    In the test: GET /v1/models returned empty list while /v1/health reported active_model_id Gemma-3-270M-It and generation_ready true

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.