pickfit

BrowseLocal AI tools

LIXBON

Self-hosted LLM gateway on a distributed GPU cluster with OpenAI API and multi-client apps.

Use it

Before you install: known vulnerabilities

pickfit found 18 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 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)
  • npm:follow-redirects 1.16.0 follow-redirects sensitiveHeaders regex escaping can expose credential headers (GHSA-8r9p-f939-6h3c, high, fixed in 1.16.1)
See 8 more

8 more findings not listed here.

Linux x86_64

You need first

  • Runtimes: Python 3.12+, Node 20+
  • System packages: Ollama

These steps ran from a folder named work in the home folder, which already existed. Make it and run them from there:

mkdir -p "$HOME/work" && cd "$HOME/work"
  1. Clean clone for replayable step

    rm -rf "$HOME"/work/Lixbon && git clone https://github.com/LIXBON-FOUNDER/Lixbon.git "$HOME"/work/Lixbon
  2. First candidate pip install clean

    pip install -r "$HOME"/work/Lixbon/requirements.txt
  3. Download install script clean

    curl -fSL -o /tmp/install.sh https://lixbon.com/install.sh
  4. Run CLI install script clean

    bash /tmp/install.sh
Verified in pickfit: the commands exactly as its sandbox ran them

For the record only: they name the sandbox's home, /home/sbx.

rm -rf /home/sbx/work/Lixbon && git clone https://github.com/LIXBON-FOUNDER/Lixbon.git /home/sbx/work/Lixbon
pip install -r /home/sbx/work/Lixbon/requirements.txt
curl -fSL -o /tmp/install.sh https://lixbon.com/install.sh
bash /tmp/install.sh
lixbon --version
lixbon status

Check that it works

lixbon --version

The output should contain “lixbon v2.14.0 linux/amd64”.

First thing to try

lixbon status

Run lixbon status to see whether the gateway is running.

What it does

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

  • Host language models on a cluster of GPU machines
    Not tested
  • Serve models through an OpenAI-compatible API
    Not tested
  • Chat from the web, desktop, command line or mobile
    Not tested
  • Direct subagents with set roles toward a goal
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. Main function works
  4. Works offline

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

Good for

  • send chat completions via OpenAI-compatible API
  • run inference on GPU nodes via Ollama
  • follow and direct CLI or desktop session from mobile

How pickfit tested it

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

Linux x86_64

Its main function works

  • Replayed from scratch
  • Works offline
  • Checked on 30 Oct 2026
  • Version 2.14.0

Differences the test machine hit

  • README: python -m uvicorn core.gateway.app:app --port 8000 --reload starts the gateway with health at /health
    In the test: Gateway needs a reachable Postgres DATABASE_URL and Ollama for inference; with no DATABASE_URL the uvicorn lifespan raises during startup, so in this box only the CLI was verified and the gateway health check was not reachable.
  • README: curl -fsSL https://lixbon.com/install.sh | bash installs the CLI
    In the test: install.sh automatically ran `lixbon init --base-url https://lixbon.com/v1` at the end and created /home/sbx/.lixbon/config.json, so `lixbon status` works offline right after install.
  • README: install step 4 runs install.sh
    In the test: nothing to change; a note: the box ran install.sh, 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.