The AI assistant who gets work done, before it slips
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
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 plan with up to $50 in free credits; Individual plan $25/month including 5,000 credits per month; Team plan with custom pricing.
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
Drafts email replies in your voice
Prepares meeting briefs automatically
Captures and tracks commitments
Updates CRM automatically
Connects to 100+ tools including Gmail, Slack, and HubSpot
Learns work patterns without workflow setup
Morning and evening digests of what needs attention
Surfaces forgotten follow-ups and open loops
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
Proactive: surfaces work that needs attention before you ask, rather than waiting for you to prompt
No setup required: builds workflows automatically from your patterns, not from a configuration wizard
Full control: everything external or consequential waits for your approval before sending or changing systems
Multi-tool context: learns across all your tools to understand your tone, priorities, and patterns
Privacy-first: data encrypted end-to-end, SOC 2 Type II compliant, and never used to train models