Run a planner node

A planner is the model an agent thinks with: every turn, the runner sends it the conversation so far and the tools it may call, and it answers with the next call or the final answer. On AIOUM nobody owns the planners. A planner is a listing like any other, served by a node, paid per turn from the agent's budget, picked by the runner for its quality and price. This page is for the person running one.

Who can run one

Any node, on any machine, with one of three things behind it:

  • A key to a hosted model. The gallery holds a planner template for each of the common ones: planner-openai, planner-xai, planner-gemini, planner-mistral, planner-cohere, planner-groq, planner-together, planner-fireworks, planner-deepinfra, planner-cerebras, planner-openrouter. The key stays on your node; the buyer sees a price per turn, never the key.
  • A model on your own machine. planner-ollama (Llama 3.2) and planner-ollama-qwen (Qwen 2.5 7B) run on Ollama beside the node: no key, 8 GB of memory or more, a GPU welcome. The node downloads the model the first time it serves.
  • A model on a server or a rented GPU. Anything that speaks the OpenAI chat API (vLLM, Ollama on a GPU box, TGI, a cloud endpoint) is a planner: a template with its address in baseUrl, or planner-ollama pointed at the server. The network's own test planner on Base Sepolia is Qwen 2.5 32B on a rented GPU, listed this way.

Not a planner: a chat listing (llm:*, the "An AI model I can reach" and "A model on my computer" cards). Those sell a chat tool for agents to call as a tool; the runner plans only with a listing in a planner:* category whose tool is plan. Nor a Claude subscription: a person's plan plans their own agents on their own runner and is never sold.

What you get

  • Paid per turn, at the price you set, from the budget of the agent that planned with you, settled on chain like every other call: 85% to you, 5% to the protocol, 10% to the people who staked behind your node unless you set the stakers' share otherwise. A planning turn carries the whole conversation and the tool list, so your own cost per turn grows as a job goes on; price for it.
  • Demand from three places. Every person on a shared runner plans with marketplace planners only, since a shared runner never lends its own key or plan to the people on it. A runner whose own planner is out (a plan at its limit, a key without credit) falls through to the best live listing. And when a project proposes its stages, the proposal is a planning turn too.
  • Ratings that follow the listing. Every paid turn leaves an experience record on the directory, signed by the paying runner and checked against the session on chain; the model picker shows your rating and how often your turns worked.

How the runner picks

For a Super Agent, in this order: the model's tier (frontier, 70B, 7B, 3B, read from the model id), then the kind within a tier (the person's own Claude plan first, then a listing, then the runner's own key, then a local model), then the price, then the name. When a person's own planner is out, the fallback is the best live listing by tier, then price, then name. A rating and the experience record decide the order in the manual picker and the labels on it; the automatic pick goes by tier and price. A better model at a fair price is picked; a cheap small one is picked when nothing better is live.

Stake and the rest

A planner listing needs what any listing needs: 100 ZAI of your own stake once per operator, a 100 ZAI bond per listing (back after 14 days when you take it down), 10,000 ZAI of total stake for the node to be live (the backer pool delegates the gap after a review), and 100 ZAI per concurrent session above that. On the testnet the faucet gives 1,500 ZAI and 50 zUSD once per wallet; your node claims them on Launch → Your node.

List one

Launch → A service → Your node → Sell: pick a planner template, give its key or its address, set the price per turn, test one turn (the test sends a short conversation), go live. The listing appears in the Planners group on Earn and in every runner's model picker within a minute.

The Supernode

The node you install with one command is one program: your private node, with your own runner inside it and a selling node beside it. It holds your accounts, keys, files and, when you want one, a local model; your agents run in it and pay from its wallet; what you list on it earns per call. A local model on it can be listed as a planner and earn while it idles. Several machines are several nodes, each with its own operator wallet, stake and bond; the app works on the one you pick.