Agent

An agent is a reusable, versioned configuration: a model (and effort), a system prompt, a toolset, skills, a required budget, and a default completion window — plus the harness field that picks the agent loop. Define it once, run it as many sessions — each a durable execution that can pause for hours at storage cost and resume exactly where it left off.

Agent reference

The full agent object, versioning, sessions, harness, completion window, budgets, and policies.

One agent, many runs

The agent is the definition; a session is a single run of it. One agent backs many sessions and cron deployments, each independently budgeted, streamed, and controlled.

One versioned agent definition fanning out to independently budgeted sessions and a cron deployment

Create one

vetta agent create --name Refunder \
  --model zai-org/GLM-5.2-FP8 --harness pi \
  --skill refund-policy \
  --budget-usd 50 --max-task-usd 5 --budget-period month \
  --window immediate --system "You process refunds."

const agent = await vetta.agents.create({
  name: "Refunder",
  model: "zai-org/GLM-5.2-FP8",
  harness: "pi",
  skills: ["refund-policy"],
  budget: { capUsd: 50, maxTaskUsd: 5, period: "month" },
  window: "immediate",
  system: "You process refunds.",
});

curl -fsSL https://api.vetta.sh/v1/agents \
  -H "authorization: Bearer $VETTA_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "name": "Refunder",
    "model": "zai-org/GLM-5.2-FP8",
    "harness": "pi",
    "budget": { "cap_usd": 50, "max_task_usd": 5, "period": "month" },
    "window": "immediate",
    "system": "You process refunds."
  }'

No computer in the config — sessions provision their own sandbox when needed.

Fields at a glance

Field	What it sets
`name` · `system`	The agent’s name and system prompt.
`model` · `effort`	Which model runs each turn, and at what effort.
`harness`	The agent loop — `pi` is the default. See How Vetta works.
`tools` · `mcp_servers`	What it may use, each gated `allow` / `ask` / `deny`. See Tools.
`skills`	Versioned expertise loaded on demand. See Skills.
`budget` (required)	The spend cap every session draws against. See Budgets.
`window`	The default completion window — cost vs. latency per request.
`output_schema`	A JSON Schema the final result must satisfy. See Structured outputs.

Every edit mints a new immutable version; the full object is in the agent reference.

Next: computer

The disposable micro-VM sandbox, filesystem, shell, and browser the agent works in.

Get started

Capabilities at a glance

Platform

Agent reference

One agent, many runs

Create one

Fields at a glance

Next: computer

Agent reference

​One agent, many runs

​Create one

​Fields at a glance

Next: computer

One agent, many runs

Create one

Fields at a glance