Naïve raises $28.5M Series A to build autonomous company infrastructure

See more ↗

Vetta Managed Agents

Vetta is a prod-ready agent harness that runs in managed infrastructure.Best for cost efficient agent workforces

Tasks passed (%) · Long Horizon Terminal Bench

Cost to host 1M agents · $ per month · cheaper →

Vetta Managed Agents

~$52k/m · 81.3% passed

Self-host Claude Code

~$740k/m · 75.0% passed

Self-host Codex

~$740k/m · 70.2% passed

Self-host Hermes

~$740k/m · 68.8% passed

OpenClaw ~$1.5M/m
Paperclip ~$1.5M+/m
VM per tenant ~$14M/m
VettaGradedCost only
100,000 tenants × 10 agents · no box held between turnsReward ↗Hosting ↗

Why Vetta?

Vetta Managed Agents provides the harness and infrastructure to deploy autonomous agents. Get a fully managed environment for your agents to browse the web, run code, and execute real-world actions.

Our vision. As intelligence becomes a commodity, companies will be built and run by millions of agents. Vetta is the infrastructure for that future.

Built for multi-tenant products.

Provision an agent per customer or team from one control plane, and run thousands of them at scale.

Built for long-horizon efficiency

It saves progress and sleeps between steps, so an eight-hour task doesn't bill you for eight hours.

Pay less when you can wait.

Name any model and how hard it should think, then pick a speed. Work that isn't urgent runs about 40% cheaper.

GLM-5.2-FP8effort: high
Any model · pick the speed

Latency

answers soon

Cost / completed task

$0.2332

Connect it to everything you already run.

It gets a shell, a real browser, your files, 10,000+ connected apps, and any MCP server you point it at.

Tasks finished (%)

Cost ($ / finished)

Loose

$0.171

Priority

$0.233

Immediate

$0.298

Claude Code

$0.872

Hermes

$1.095

Pi

$1.102

Codex

$1.359

VettaOthers
terminal-benchView all benchmarks ↗

Built for production

An agent is a few lines of code.

A typed client, a CLI, and a REST endpoint, with the same operation in all three. The spend cap is part of the config, so every agent has a ceiling from the moment it exists.

import Vetta from "@usenaive-sdk/vetta";

const vetta = new Vetta();

const agent = await vetta.agents.create({
  name: "nightly-triage",
  model: "zai-org/GLM-5.2-FP8",
  system: "You are a concise triage agent.",
  window: "loose",
  skills: ["triage-policy"],
  budget: {
    cap_micro_usd: 50_000_000,
    max_task_micro_usd: 5_000_000,
    period: "month",
  },
});