AI desktop assistant that reads your screen and guides you step by step through any task in real time
A persistent team of coding agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
BG
Not given
Pricing model
Freemium
Open source
Pricing
Free plan: $0/month with 250 daily credits (about 4-8 guided tasks per day), no card required. Unlimited plan: $9.99/month with unlimited credits and no daily cap, cancel anytime. Full refund available within 14 days of purchasing Unlimited.
Not given
Key features
Reads your screen in real time and provides step-by-step guidance on what to click
Works across any software, website, or app without plugins or integrations
Available on Windows and macOS
Voice and text input in any language
Three thinking modes to balance reasoning and speed
Encrypted end-to-end communication
Never stores, logs, or retains screen data
Does not train AI models on user data
User remains in full control, no automatic actions
Only reads screen when actively requested
Start teams with one command and manage agents across multiple machines
Mix Claude Code, Codex and Pi agents in one team
Agents delegate and coordinate work with named task assignments and queue ownership
Agents message each other directly and read each other's screens
Restore agent conversations after restart or reboot from snapshots
Choose different models and reasoning effort per agent
Bring custom harnesses and integrate with MCP servers and Claude Desktop
Start Docker Compose services alongside agent teams
Control message filtering with typing guards and chat broadcasts
What makes it different
Only AI assistant that reads your actual screen and points directly to what you need instead of explaining in generic text
Works with any software or website without needing individual app connections or plugins
Saves significantly more time than traditional AI chatbots by keeping you in your workflow
Guides you through tasks rather than replacing you, keeping you in control at all times
Comprehensive privacy and security with no background access or data collection
One conversation interface with a lead agent coordinating specialists behind the scenes
Mix multiple coding models and harnesses in one managed team
Run entirely self-hosted on your own machine with no external coordination
Open source with Apache 2.0 license and extensible harness contracts