pickfit

BrowseLocal AI tools

AirDrop-LLM

Offline P2P broker pooling laptops over Wi-Fi for pipeline-parallel LLM inference.

Tested on Linux

Use it

Linux x86_64

You need first

  • Needs the network
  1. npm install -g airdrop-llm@latest

    npm install -g airdrop-llm@latest
Where the README and reality differ
  • README: airdrop start spawns model and daemon directly
    What worked: CLI wrapper `airdrop start` tries to spawn `ollama serve` and crashes with ENOENT if ollama not installed; running daemon directly via `node bin/airdrop-daemon --mode master` bypasses that and still exposes gateway on :9995

Check that it works

node ~/.local/lib/node_modules/airdrop-llm/bin/airdrop-daemon --mode master --ui-port 3000 --ws-port 3001 2>&1

The output should contain “OpenAI-compatible reverse proxy listening at http://localhost:9995/v1”.

First thing to try

node ~/.local/lib/node_modules/airdrop-llm/bin/airdrop-daemon --mode master --ui-port 3000 --ws-port 3001 2>&1

Start the master node with airdrop-daemon --mode master --ui-port 3000 --ws-port 3001.

What it does

  • Pool laptops into one GPU cluster
    Not tested
  • Run 32B and 70B models offline
    Not tested
  • Serve an OpenAI-compatible chat completions API
    Not shown working
  • Find other laptops over Wi-Fi
    Not tested

How far pickfit got

Linux x86_64

  1. Installs
  2. Starts
  3. 0 of 4 features work
  4. Works offline

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

Good for

  • Run 32B and 70B parameter models across pooled laptops
  • List available cluster models via OpenAI gateway
  • Stream distributed chat completions via API gateway

An alternative to Ollama / llama.cpp, Petals and Cloud APIs (OpenAI/Anthropic).

How pickfit tested it

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

Linux x86_64

Installs and starts

  • Replayed from scratch
  • Works offline
  • Checked on 31 Oct 2026
  • Version 0.1.6

Differences the test machine hit

  • README: npm install downloads Rust binary via postinstall
    In the test: postinstall attempts GitHub binary download; on this Linux x64 box binary was a 57K Node.js shim not Rust binary, fallback to Node daemon works without Rust toolchain

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.