Autonomous AI workers and operating system for people and agents
The new interface for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
DE
Pricing model
Not given
Freemium
Pricing
Not given
Free: €0/month with 25 on-screen requests per month, 2 projects, and 5 connected tools. New users get a 14-day Pro trial. Pro: €19/month or €199/year for unlimited on-screen requests, unlimited projects, unlimited integrations, knowledge graph memory, and priority support. AI provider charges are se
Key features
Persistent agent identity with continuing responsibility
Model independence with agent-selected models from approved garden
Wand Registry for centralized human and agent roles and authority
Wand Teams for coordinated processes between humans and agents
Wand Governance for aligned policies and objectives
Learning and experience accumulation across assignments
Model selection optimization based on patterns and outcomes
Agent Runtime Hours for measuring autonomous capacity
Measured business value tracking including quality, cost and autonomy
Computer use: clicks, types and fills forms in apps
Voice dictation and screen marking
Memory that learns user details and reuses them
Parallel agents running simultaneously
On-screen guidance showing where to click
Integrations with Gmail, Slack, Notion, GitHub and more
Task board to track running, done and waiting tasks
Projects as workspace homes with tasks, chats and results
Skills: save and reuse how you do a job
Works with Claude Code, Codex and OpenCode
What makes it different
Agents carry identity, authority and accumulated experience across assignments
Model independence allows agents to choose from frontier and open-source models
Single platform coordinates humans and agents with shared roles and governance
Compounding efficiency through recurring pattern optimization
Supports both enterprise operations and national AI labor capacity building
Works directly on your screen in your apps instead of forcing you to a chat window
Visual input through pointing, drawing, and marked screenshots instead of text prompts
Full user control: asks before acting and shows cursor while working
Remembers user details and context across tasks
Voice-based task dispatch from any app you're already using