For AI agents

Mask it. Prove it.

The privacy and proof layer for AI — for people and agents.

AI agents read your files, your terminal and your configs, and send them to an AI on their own — no person checks each request. Omna masks every one on your device before it leaves, and leaves a receipt for each.

$curl -fsSL https://omna.dev/cli/install.sh | bash
Free · Mac & Linux · Claude Code is covered automatically
You ask Claude CodeRead customer.env, write deploy.sh, then spell the AWS key backwards.
Claude Code answers“…every value showed up as a label in square brackets, not a real value. For the key ID, that label was AKIAIOSF…EXAMPLE. Spelled backwards, that label is ]1_YEK_SWA_TERCES[. … I never saw a real key.”
What happenedOmna put the real key back in what you read. Spelled backwards, it gives the game away: Claude only ever saw [SECRET_AWS_KEY_1].

A real Claude Code run through Omna on your computer, with fake data. Answer shortened.

Agents need it more than people do.

They read everything

Whole files, .env files, logs and terminal output — exactly where keys and customer data live.

Nobody checks each send

One task can be many requests to the AI, all sent on their own. Omna checks every one, every time.

They write back to your files

Omna puts names and emails back in what the agent writes, so its edits still work. Keys and passwords stay as labels there, so a trick can't send them anywhere.

How it works with an agent.

01

The agent sends a request.
Omna catches it.

On your computer, before it leaves — with your own key or login, to the AI you already use.

02

Omna masks it.
The AI sees labels.

A key becomes [SECRET_AWS_KEY_1], an email [EMAIL_1]. Real values come back in the answer you read. In the agent's commands and files, only personal data comes back — never a key.

03

Every request gets a receipt.
You get the report.

Which agents ran, how many requests, and what was caught — counts only, never content.

Works with the agents you use.

Automatic

Connected by the install line, if they're on your computer.

Claude CodeCodex CLIaiderVS Code (Copilot Chat)Continue

One setting, typed once

Paste Omna's address into the tool's settings.

CursorClineWindsurf

Every supported tool, and what isn't covered yet ›

Building your own agent?

If it uses the Anthropic or OpenAI SDK, point it at Omna — one line. Everything else stays the same: your key, your model, your code.

Read the agent docs ›

Anthropic SDKexport ANTHROPIC_BASE_URL=http://127.0.0.1:7788
OpenAI SDKexport OPENAI_BASE_URL=http://127.0.0.1:7788/v1

Built to fail safe.

Stopped means stopped

If Omna isn't running, agents can't connect at all. Nothing leaves unmasked.

Labels, never look-alikes

Agents always get labels like [EMAIL_1], never fake values — a fake email could be committed by mistake; a label can't hide.

Nothing sent to us

The only place a request goes is the AI you were already using. Receipts stay on your computer.

Protect your team in one line.

Free for the first 10,000 users · Mac & Linux

$curl -fsSL https://omna.dev/cli/install.sh | bash