Let AI agents work in your signed-in Chrome browser with scoped access, human approval, and verified results
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Not given
Pricing
Cloud compute: $0.461/hour while awake, $0 when idle or parked. Models priced at or below maker's rate. Example: Claude Opus 5.5 with $0.461/hour compute, or $0 model usage if using Claude Pro/Max subscription. Prepaid credits start at $10. Card top-ups include Stripe fee (2.9% + $0.30).
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).
Key features
Browser-based agent access
Agent API for integration
Multi-channel deployment via Slack and other apps
Native Mac app
Cloud-based agent execution
Bring your own Claude or ChatGPT subscription
Usage-based pricing with per-second compute metering
Agent skills for reusable instructions
Agent marketplace with 64+ agents
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
What makes it different
Access any agent in one place without per-agent switching
$0 model costs when using your Claude Pro/Max or ChatGPT Plus/Pro subscription
Cloud agents that cost $0 while parked or idle
Reusable agent skills that inject domain expertise automatically at runtime
Multi-channel deployment from browser to Slack to Mac without code
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