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. Many owners. One network.

Contributors share

Your computer runs open models with llama.cpp and earns credits for the answers it serves. 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

Honest about what works today.

Answers are checked

Hidden test prompts and vetted reference contributors check answers 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 contributor reports.

Streams, with failover

Tokens arrive as they are produced; if a contributor fails, another one continues without duplicating work.

Know the limits

The computer that answers can read your messages, so do not send secrets. Credits have no cash value. Today each model runs whole on one contributor; splitting one model across many machines is in the lab.

Contribute

Your spare GPU, working for the community.

  1. 1

    Get an invite

    The beta is invite-only. The operator, who runs the coordinator, sends you a join code.

  2. 2

    Install and join

    Use the installer for macOS, Windows or Linux, or run noduma contribute --join <code>. It starts at login.

  3. 3

    Earn compute

    Every answer your machine completes 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. Point your OpenAI client there and keep your code.

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.