What is an operator
ZeroSignal doesn't run the AI models its users talk to. They're served by operators: independent parties who run inference hardware and sell its output on an open network. If you have GPUs and a model to serve, you can be one.
If you're a user rather than an operator, see The operator network.
You add yourself as an operator, and add each node, at the operator dashboard: operator.zerosignal.ai. Connect your owner wallet there. There's no sign-up form and nobody to approve you. See Registering on-chain for what you're publishing.
What an operator does
An operator runs the node software in front of an AI backend and registers on-chain with their owner wallet. Once registered, the node:
- Advertises the models it serves, their prices, and its capabilities, so users' clients can discover it.
- Answers inference requests: it receives an encrypted prompt, runs the model, and streams back an encrypted reply.
- Gets paid per request in dollars (USDC), settled on-chain against a price the user agreed to up front.
- Relays other operators' traffic, which protects every user's network identity. Every node is also a relay. Relaying is mandatory and unpaid.
There's no application and no gatekeeper: the registry is a smart contract, so anyone can register and any user can transact with any operator. You set your own models, prices, and policies. How the network works covers the economics and trust model.
Operators and nodes
An operator is an on-chain identity: an owner address that gets paid and a stake that backs it. Under that identity you run one or more nodes. Each node is a single running endpoint with its own URL and signing key.
Users' clients route to a node, not to the operator as a whole. That lets you:
- Run several machines under one operator identity and one payout address.
- Bring a node up in staging to test it without taking production traffic.
- Take a node down for maintenance while your other nodes keep serving.
Economics, stake, and reputation accrue to the operator. Reachability, latency, and throughput are tracked per node.
What you need
| You need | Why |
|---|---|
| Inference hardware | Capable of serving the model(s) you want to offer, plus a backend that runs them. |
| A public HTTPS endpoint | The node software listens on it. Users' clients must reach it, and so must other operators, since you'll also relay. |
| Two Algorand accounts | A cold owner account for your operator identity and payouts, and a hot signing account whose key lives on the node. |
| A USDC stake | $250, locked in the protocol to register (see Staking & economics). |
| The node software | Prebuilt binaries under the Functional Source License (FSL-1.1-ALv2). It advertises your catalog and speaks the wire protocol. |
What's covered here
Get oriented
- How the network works — the economics and the trust model from an operator's point of view.
- Quick start — the fastest path from zero to serving a first request.
- Operator dashboard — where you create your operator record and add nodes.
Running a node
The concept, configuration, and on-chain pages are complete. Two things are
still settling: the node-software CLI command and flag names (the commands
in the CLI reference are real but may be renamed), and the byte-level
wire-protocol specification (the concept pages cover behavior, not the JSON
layout). A full protocol specification is coming soon. Confidential compute
(TEE) works today as dstack-tdx (Intel TDX), and the GPU
confidential-computing modes aren't ready yet; see the status note in
Confidential compute.