Invite-only beta · live on a community network

The world is one big datacenter. Let's connect it.

Share your GPU and RAM. Run AI. Earn compute for your own models.

How it works

Many computers. One network. No single owner.

Contributors share

Your machine runs an open model with llama.cpp when it is idle. One command installs a pinned, verified engine and keeps it running.

The coordinator routes

Each request goes to a ready, fast contributor. If one fails, the answer moves to another. It never runs models and never stores prompts or answers.

Consumers run AI

Chat in the browser or point any OpenAI-compatible tool at Noduma. Researchers get affordable access to open models.

Built on trust you can check

Honest about what works today.

Answers are checked

Vetted reference contributors re-run a sample of answers and score them token by token. Only checks move a contributor's trust, and low trust suspends.

Fair billing

Credits come from what the coordinator measures, never from what a node reports.

Streams, with failover

Tokens arrive as they are produced; a failed node hands over without duplicating work.

Know the limits

The computer that answers can read your messages, so do not send secrets. Credits are not cashable yet. Today each model runs whole on one contributor; splitting one model across many machines is in the lab.

Contribute

Your idle GPU, working for the community.

  1. 1

    Get an invite

    The beta is invite-only. The operator sends you a join code.

  2. 2

    Install and join

    macOS, Windows or Linux. Run noduma contribute --join <code>; it starts at login.

  3. 3

    Earn compute

    Every answer your machine serves earns credits to run models yourself.

Developers

OpenAI-compatible. Change one URL.

Use your API key with /v1/models and streaming /v1/chat/completions at https://app.noduma.dev/v1. Works with the OpenAI SDKs and the tools built on them.

Try it in the chat
request.sh
curl -N https://app.noduma.dev/v1/chat/completions \
  -H "Authorization: Bearer $NODUMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen2.5-1.5b-instruct-q4_k_m",
       "stream": true,
       "messages": [{"role": "user",
                     "content": "Hello"}]}'

The world is one big datacenter.
Let's connect it.