Always-on · Works while you sleep · Any task

Zoyya acts.
You watch.

Open a tab. Ask. Approve. Walk away.

Live · running now
YouSomeone asked
Research Bali flight options for next Friday.
Search

Built for people who delegate the busywork

FoundersAgenciesIndie developersOperations leadsResearchersMarketers

Built for the way you work.

Always-on

Runs while you sleep. Picks back up when you log in.

Any task

Anything a human can do on a computer. Book, monitor, draft, deliver.

Stays in line

Approvals, rate limits, and a full record of every action it takes.

Your choice of AI

Pick the model that fits the task. Change your mind anytime.

Approval rules when you need them

Default to fast full-access runs, or require approval for selected tools in Governance.

Plays well with your tools

Connects to Slack, GitHub, Linear, Notion, Google Drive, Telegram, and webhook-based workflows.

Real asks. Real outcomes.

Book me a flight to Bali next Friday.

Compared 14 fares across 4 airlines. Held seat 23A on SQ11. Waiting on your confirm.

Monitor my competitor's pricing and alert me when it changes.

Checking every 15 minutes. Caught a 26% drop on their Starter tier at 03:42. Pinged you on Slack.

Draft next week's announcement and schedule it.

Wrote it in your voice. Trimmed 18 filler words. Queued the follow-up run for Tuesday 9am.

Simple pricing. Just the agent.

Start free. Pay only when it’s doing real work for you. See every limit →

Free
$0forever

Free workspace. No card required.

  • 1M LLM tokens · 50 runs / mo
  • 1 concurrent run
  • Auto model routing
  • Community support
Get started — free
Lite
$15/ month

Real work, everyday tasks — at a starter price.

  • 5M LLM tokens · 500 runs / mo
  • 3 concurrent runs
  • Schedules · triggers · webhooks
  • Community support
Start Lite
Most popular
Pro
$39/ month

Sharper reasoning for indie devs, freelancers, founders.

  • 8M LLM tokens · 2K runs / mo
  • 10 concurrent runs
  • Schedules · triggers · webhooks
  • Email support
Start Pro
Max
$99/ month

The smartest models on every task, plus team-grade governance.

  • 10M LLM tokens · 20K runs / mo
  • 50 concurrent runs
  • Approval workflows + audit log
  • Priority support
Start Max

Built so you can sleep at night.

Read the full security overview →

Isolated workspaces

Each org runs in an isolated shared sandbox with strict permissions, capped resources, and no path back to the host.

Network policy

Browser and fetch requests block private-network targets. Teams can also lock sandbox egress entirely.

Secrets vault

Credentials are encrypted at rest, redacted from traces, and can be kept out of the sandbox when needed.

No training on your data

We don't train models on your prompts, files, or outputs. You choose the LLM provider and model for each workspace.

Common questions.

What if it gets something wrong?

You see every step as it runs, can stop an active task, and can resume paused or halted runs with follow-up instructions. Mistakes are logged so you can correct course next time.

Will it ask before sending or paying?

Not by default. ZOYYA starts in Bypass mode, so the agent runs allowed tools without pausing. Turn on Ask permission in Governance to require approval for selected tools.

What can't it do?

It won't act on apps you haven't connected. It won't claim a result it didn't verify. It won't run when you're over your plan limit without telling you.

Is my data used to train AI models?

ZOYYA does not train models on your prompts, files, or outputs. Task content is sent to the LLM provider you configure, so provider-side handling follows that provider's terms.

Can I pick which AI model it uses?

Yes. Choose a managed ZOYYA router for your plan, or configure your own provider key. Above-plan managed routers are locked until you upgrade.

Set it.
Forget it.
Watch it work.

Get started — free
ZOYYA · the AI agent that does the work