| What it does | Let AI agents work in your signed-in Chrome browser with scoped access, human approval, and verified results
| A personal AI agent your family can share
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Not given
| Free trial
|
|---|
| Pricing | Free: €0/month with 100 task credits per month and 1 connected browser. Pro: €5/month with 2,000 task credits per billing month and 5 connected browsers. Extra credits: 1,000 credits for €3 on Pro (do not expire).
| Free trial with 25 credits (15-25 tasks). Personal Plan: $9.99/month (50 credits/month, 1 member). Group Plan: $19.99/month (150 credits/month, up to 6 members). Group Plan Max: $99.99/month (1,000 credits/month, up to 10 members).
|
|---|
| Key features | - Redacted sensitive values including passwords, OTPs, card data, and API keys
- Effect verification to prevent blindly repeating uncertain browser side effects
- Integration with ChatGPT and Claude via MCP connectors
- REST API and custom agent key support for own scripts
- Task credit model with no separate browser-hour or AI model billing
| - Plan trips with resorts, flights, and shared itineraries
- Tidy inbox with morning digest and draft replies
- Manage calendar with appointments, forms, and reminders
- Monitor prices and alert when thresholds are reached
- Review, edit, or delete all saved facts in plain English
- Approve every email, calendar invite, or external action before execution
- Gmail and Google Calendar connectors
- Monitor and summarize Gmail mailbox for family activities
- Research and compare products and local services
|
|---|
| What makes it different | - Keeps your signed-in sessions in your own Chrome profile instead of copying them to a remote browser fleet
- Brings the agent into your existing browser instead of moving your browser to a remote server
- Charges only for accepted tasks, not for browser hours or AI model calls
- Prevents uncertain side effects from being blindly replayed through durable task state and effect verification
- Treats all page content as untrusted data so websites cannot grant themselves new permissions
| - Human-in-the-loop approval for every action before it executes
- Transparent memory with plain-English facts you can edit or delete
- No ads, no data harvesting, no training models on user data
- Built by infrastructure veterans from Meta, Amazon, and earlier startups
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 3 ▲ +1 (up) since last check |
| Trust Flow (Majestic) | 6 | 0 |
| Citation Flow (Majestic) | 22 | 16 |
| Referring domains (Majestic) | 8 | 7 |