Get started

Run a model, flip the switch

LAPSUS is a small local app — it sits in front of the model you already run, and joins you to the community network. Packaged one-click downloads for macOS, Windows and Linux are on the way; until then it runs from source.

Share your AI

  1. Start LM Studio (:1234) or Ollama (:11434) and load a model.
  2. Open the LAPSUS app.
  3. Flip the Share switch on — you're part of the network.
  4. Switch it off (or quit the app) and you're disconnected instantly.

Optional: cap how much you give (e.g. 25% of idle time) and set rate limits.

Use the network

  1. Open the Use AI tab.
  2. Pick a community model, type a prompt, hit Ask.
  3. The answer comes back over a direct encrypted channel.

Remember: offer some then get some. Sharing earns credits; using the network spends them.

Running it today

The agent app is open and runs locally with Elixir while packaged builds are prepared:

# Run from source — needs Elixir + Rust.
git clone https://github.com/pythononwheels/lapsus.git
cd lapsus && mix deps.get
LAPSUS_COORDINATOR_URL=wss://lapsus.pyrates.io mix lapsus.app   # opens the local app

# Or a self-contained binary (bundles the runtime, defaults to the live
# network — no Elixir needed to run it):
MIX_ENV=prod mix release lapsus
LAPSUS_RUN=1 _build/prod/rel/lapsus/bin/lapsus start
        

          The app talks to the community coordinator at wss://lapsus.pyrates.io. Prompts
          and answers never pass through it — they go directly peer to peer.