AI assistant that automates desktop tasks by learning from your actions
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
US
Pricing model
Freemium
Freemium
Pricing
Prepaid compute at $0.02 per compute-unit hour. Minimum $5 top-up with no monthly subscription. Machine rates: Lite $0.02/hour, Small $0.12/hour, Medium $0.20/hour, Large $0.32/hour, XL $0.56/hour. Open source platform available via GPLv3 license for self-hosting on Cloudflare (Workers Paid plan sta
Free: $0 per user with 10 included workflow runs and basic features. Plus: $20 per seat per month with expanded usage. Pro: $100 per seat per month with 5x more usage than Plus. Annual billing available at 20% discount. Enterprise plans available with custom pricing.
Key features
Linux workspace with command execution, file operations, and tool installation
HTTP API, SSH, and browser terminal access
Account-owned lifecycle controls and explicit ownership
Five machine sizes from Lite to XL
Saved workspaces with snapshot stop and resume
Prepaid balance with no monthly subscription
Shared accounts and billing infrastructure
Hosted apps including Linux computers, Vibe coding, and Voice agents
Custom runtime images and language support
Outbound internet and ephemeral storage
Learn tasks by demonstration - show once, replay automatically
Works with existing apps via screen automation without integrations
Voice command interface
Team collaboration with shared playbooks
Automatic workflow detection and updates when apps change
Scheduled task automation
Manual and automatic approval modes
Content generation with image and music creation
Knowledge base for team documentation and context
What makes it different
Open-source platform that can be self-hosted on own Cloudflare account
Built-in accounts, billing, and metering so developers don't start from scratch
Simple prepaid model with no monthly commitment
Direct founder contact for product feedback and integration questions
Account-owned HTTP workflow with automatic cleanup
No integrations required - uses screen automation like a human would
Learns by watching - no code or complex setup needed
Automatically adapts when app interfaces change
Voice-controlled AI that understands context from your screen
Full team access to shared automations and knowledge base