pickfit

BrowseLocal AI tools

lilbee

Local AI stack in one executable that runs models and searches files, code and web with citations.

Tested on Linux

Use it

Linux x86_64

You need first

  • Runtimes: Python 3.11 to 3.14
  • At least 8 GB of RAM
  1. npm install -g lilbee

    npm install -g lilbee

Check that it works

which lilbee && lilbee --version 2>&1

The output should contain “0.6.90b691”.

First thing to try

lilbee self-check 2>&1

Run lilbee self-check first to confirm the tool works on your system.

What it does

  • Run and manage local AI models
    How to use it
    1. Run lilbee self-check to confirm the tool is working.
    2. Run lilbee model list to see which models are installed.
    Tested
  • Ask a search engine and get cited answers
    Not tested
  • Crawl websites into your local library
    Not tested
  • Serve coding agents as an MCP server
    Not tested

How far pickfit got

Linux x86_64

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

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

Good for

  • search files, notes, code and web with cited answers
  • crawl websites into local library
  • run coding agents on local models

An alternative to Ollama and LM Studio.

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
  • Needed the network
  • Checked on 30 Oct 2026
  • Version 0.6.90b691

Differences the test machine hit

  • README: npm install -g lilbee then lilbee self-check
    In the test: first lilbee invocation downloads ~398MB standalone binary to ~/.cache/lilbee-npm and then runs
  • README: lilbee add files then ask
    In the test: after pulling models, run use-embedder to set embedding_model before add; chat model still unconfigured so ingest/ask needs more setup

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.