pickfit

BrowseLocal AI tools

Jan

Open-source ChatGPT alternative that runs LLMs offline on your computer.

Tested on macOS and LinuxKnown vulnerabilities

Use it

Before you install: known vulnerabilities

pickfit found 8 known high or critical vulnerabilities (13 findings, one per affected package version) in the packages a fresh install brings (OSV.dev, 5 Nov 2026). Weigh this before you install it.

  • crates:calamine 0.37.0 Panic and unbounded allocation (OOM) in the CFB/OLE2 parser on malformed input (RUSTSEC-2026-0436, high, fixed in 0.38.0)
  • crates:pulldown-cmark 0.13.4 Exponential event growth with `ENABLE_WIKILINKS` (RUSTSEC-2026-0414, high, fixed in 0.13.5)
See 8 more

3 more findings not listed here.

macOS arm64

You need first

  • Runtimes: Node.js ≥ 20.0.0
  • System packages: Make ≥ 3.81
  • A GPU is optional
  1. Install Jan macOS app via brew cask

    mkdir -p ~/Applications && brew install --cask --appdir=$HOME/Applications jan

First thing to try

open ~/Applications/Jan.app

Linux x86_64

You need first

  • Runtimes: Node.js ≥ 20.0.0
  • System packages: Make ≥ 3.81
  • A GPU is optional
  1. Download Jan 0.8.8 AppImage from GitHub releases

    mkdir -p ~/apps && curl -fL -o ~/apps/Jan.AppImage https://github.com/janhq/jan/releases/download/v0.8.8/Jan_0.8.8_amd64.AppImage
    chmod +x ~/apps/Jan.AppImage
  2. Extract AppImage with --appimage-extract (FUSE not available)

    cd /tmp && rm -rf squashfs-root && ~/apps/Jan.AppImage --appimage-extract

First thing to try

/tmp/squashfs-root/AppRun

What it does

  • Download and run local LLMs
    Tested
  • Connect to cloud AI models
    Not tested
  • Create specialized AI assistants
    Not tested
  • Serve OpenAI-compatible local API
    Not shown working

How far pickfit got

macOS arm64

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

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

  • download and run LLMs offline
  • connect to cloud AI models
  • create specialized AI assistants

An alternative to ChatGPT.

How pickfit tested it

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

macOS arm64

A feature worked when operated

  • Replayed from scratch
  • Checked on 4 Nov 2026
  • Version 0.8.8

When pickfit opened it, its first-run (setup) screen rendered. pickfit then used it, and this worked: Download and run local LLMs. The launch passed again with the network off.

Differences the test machine hit

  • README: download jan.dmg from app.jan.ai/download/latest/mac-universal or GitHub Releases
    In the test: installed published macOS build via Homebrew cask to ~/Applications: mkdir -p ~/Applications && brew install --cask --appdir=$HOME/Applications jan

Linux x86_64

It opens to its first-run screen

  • Replayed from scratch
  • Checked on 4 Nov 2026
  • Version 0.8.8

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: Download jan.deb or jan.AppImage and run
    In the test: AppImage cannot mount without FUSE (fusermount missing); must extract with --appimage-extract and run /tmp/squashfs-root/AppRun with DISPLAY=:99
  • README: Build from source with make dev / Rust+Tauri
    In the test: Prebuilt AppImage is the practical install; building from source requires Rust toolchain and is slow, last-resort
  • README: install step 2 runs Jan.AppImage
    In the test: nothing to change; a note: the box ran Jan.AppImage, downloaded, without reading it first, so pickfit did not inspect it

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.