pickfit

BrowseLocal AI tools

Tabby

Self-hosted AI coding assistant for code completion and chat.

Use it

Before you install: known vulnerabilities

pickfit found 49 known high or critical vulnerabilities (54 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:lettre 0.11.7 lettre has TLS hostname verification disabled when using Boring TLS backend (GHSA-4pj9-g833-qx53, critical, fixed in 0.11.22)
  • crates:zip 2.6.1 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 8 more

44 more findings not listed here.

Linux x86_64

You need first

  • A GPU is optional
  1. download binary tarball from GitHub releases

    curl -fL -o /tmp/tabby.tar.gz https://github.com/TabbyML/tabby/releases/download/v0.32.0/tabby_x86_64-manylinux_2_28.tar.gz
  2. extract and install tabby binary to ~/.local/bin

    mkdir -p ~/.local/bin && tar -xzf /tmp/tabby.tar.gz -C /tmp && cp /tmp/tabby_x86_64-manylinux_2_28/tabby ~/.local/bin/tabby && chmod +x ~/.local/bin/tabby; ~/.local/bin/tabby --help
  3. install co-located llama-server binary required for serve

    cp /tmp/tabby_x86_64-manylinux_2_28/llama-server ~/.local/bin/ && chmod +x ~/.local/bin/llama-server
Where the README and reality differ
  • README: install from tabby_x86_64-manylinux_2_28.tar.gz
    What worked: must also place llama-server binary alongside tabby in same directory or serve crashes with 'Failed to locate llama-server binary'

Check that it works

curl -i http://127.0.0.1:8085/v1beta/server_setting 2>&1
curl -s -w "%{http_code}" -o /tmp/out.txt http://127.0.0.1:8085/v1beta/server_setting && cat /tmp/out.txt && echo "CODE" && cat /tmp/out.txt
tabby --version

The output should contain “tabby 0.32.0”.

First thing to try

tabby serve --port 8085 --device cpu 2>&1

What it does

  • Complete code with repository context
    Not tested
  • Answer questions via Answer Engine
    Not tested
  • Chat and edit code in IDE
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 3 features work
  4. Needs the network

Good for

  • complete code with repository context
  • answer developer questions from internal data

An alternative to GitHub Copilot.

How pickfit tested it

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

Linux x86_64

Its service answers requests

  • Replayed from scratch
  • Needed the network
  • Checked on 4 Nov 2026
  • Version 0.32.0

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.