Your data, account access, and AI requests.

The short version

• Your data stays local

  History, bookmarks, chats, scheduled tasks, and run logs are files on your machine. We run no server that receives them, so there is nothing of yours for us to hand over, sell, or lose.

• Inference does not, unless you run a local model

  AI requests go to the provider or endpoint you select. An endpoint running on this device keeps inference on this device.

• Nothing you send trains a model

  Aera configures OpenRouter to exclude endpoints that train on request data. Requests to your own endpoint follow its configuration and policies.

• Your own browser profile, not a bot harness

  Aera drives the Chromium profile on your machine, in the sessions you are already signed in to. There is no headless fingerprint and no handoff of your passwords to a cloud runner.

• Local-first, not offline

  Your account, a session check at launch, update checks, and billing amounts do leave your machine. The full list is further down this page.

What stays on your machine

These files are stored in your Aera profile folder. Aera does not collect them on its servers. Use the privacy controls to manage local browser data.

Browsing history

Every page you visit, in the same local database Chromium uses.

Bookmarks and saved passwords

Stored on your device by Chromium, the same way Chrome stores them.

Chats with the agent

Every conversation, including the page text the agent read in order to answer, in a local database.

Scheduled tasks and run history

The task, its schedule, and the step-by-step log of every run it made.

Skills and files

Skills you write, and files the agent produces, sit on your disk. A skill stays local until you choose to publish it to the marketplace.

Where inference goes

AI requests are made when you use chat or an automation you create or ask the agent to create. An automation can then run on its schedule or configured triggers without another click. Opening or reading a page on its own does not send that page to a model.

Models accessed through Aera

The request goes from your machine to OpenRouter, which routes it to the provider serving the model you picked. For frontier models that is the model's own company, such as Anthropic, OpenAI, Google, or xAI. For open-weight models it can be another company that hosts them. The request does not pass through an Aera server.

Your configured model endpoint

The request goes to the model server you entered in Settings > Models, which is an address on your own machine by default. Nothing goes to OpenRouter and nothing goes to us. Chat titles, suggestions, and history compaction run on that same local model.

What a request contains

Your instruction, the text of the page, and the earlier turns of that conversation. Also a screenshot, when the model has to see the layout, and any file you attached.

What we never receive

We run no models and keep no copy of a request. Aera's own servers exist for accounts, billing, updates, and the marketplace.

Account and service connections

Aera connects to services for accounts, updates, billing, and marketplace actions. The connections below apply alongside the model request path.

Your account

Your name, email address, and plan are stored on Aera servers for account access and billing. Sign-in is required to use the agent.

A session check at launch

When Aera starts it asks our server whether your session is still valid. The request carries your Aera version, your platform, a device fingerprint, and the identifier the installer brought from our download page, and we store it with your IP address and user agent. That is how we match a download to the install that followed it, and how we keep one person from collecting referral rewards or free credits as though they were several.

One install event

The first time a new install launches, Aera sends a single event that says so, with the same fingerprint. It is how we tell a download apart from an install that actually ran. It carries no URL and no page content.

Update checks

Aera asks our update endpoint for the current version, sending its own version, platform, and release channel. No account and no cookie ride along.

What you spent

For billing we reconcile the dollar amount of model usage on your key. We receive amounts. Not prompts, not page content, not the model's answers.

The marketplace

Installing a skill increments a public counter for that skill. Publishing one uploads the skill you wrote. Nothing else about your browser goes with it.

Using a local model

Connect a model server such as Ollama in Settings > Models. The request goes to that endpoint. It stays on this device when the server runs on this device.

Permissions and untrusted content

Aera works in your accounts with the permissions you grant. Review access for saved sign-ins and connected tools, and give your manager clear boundaries for the work.

Prompt injection is real

Pages can contain instructions intended to redirect an agent. Aera treats page content as data. Limit account and connector access to the work you authorize, and use run history to inspect actions.

The agent works inside your signed-in sessions

Aera can act in the accounts you authorize. Your manager uses the permissions you grant and asks for approval when the work falls outside them.

Local connectors run with your permissions

An MCP connector you install runs as an ordinary process under your own user account, with the access that gives it. Install ones you would trust with that.

No compliance certification

Aera does not hold SOC 2 or ISO 27001 certification. Use the technical details on this page and the privacy policy when reviewing your requirements.