Skip to main content
Vetta is a managed agent for long-horizon tasks, optimised for cost at every layer. You configure the whole agent — model, system prompt, tools, skills, budget, completion window, and the harness that runs the loop. Vetta operates all three layers below so that a finished task costs as little as possible.

​
The three layers

The three layers: harness, tools, and the runtime
Optimising all three together is the product — a cheap model on a wasteful loop, or a tight loop on infrastructure that bills an idle machine, both end up expensive.

​
The harness (harness)

The harness is the agent loop: assemble a turn, call the model, parse tool calls, decide what carries into the next turn. It is configurable per agent, and pi is the default:
The field is a stable seam: switching harnesses for one agent changes nothing about the durable loop, the budget gate, the tool surface, or the policy layer beneath it. Which loops exist, what each can be admitted for, and what an idle session on one costs are all in Harnesses — and readable at runtime from GET /v1/harnesses, because a harness needs an adapter compiled in and an environment can have a different set.

​
The runtime

The runtime is everything under that seam — the managed infrastructure every agent runs on:

​
The durable loop

The durable loop: wake, one bounded turn, commit, sleep, repeat An hours-long run is a sequence of bounded turns, not a machine held hot. Only the turn is metered compute; between turns the micro-VM is paused, so waiting meters storage. State commits every turn — a crash costs one turn, never the run.

​
The tools

One interface to a computer, a browser, storage, skills, identity, connections, and MCP servers. Every call passes policy — allow / ask / deny — and is priced before it runs. What this stack does to cost per finished task is measured on the published benchmark.

Next: the completion window

Three prices for one model, chosen per request.