€20 per agent per month, or €200 per agent per year (ten months for twelve). Each agent includes 1,000 inference credits per month. Custom plans available for specific deployment needs.
Free: up to 2 agents, 1 group chat, 100 messages a day. Pro: $10.49 a month at launch (Launch price. After launch, Pro will be $19.99 a month for new subscribers). Pro includes unlimited agents and group chats, 150 messages an hour and 3,000 a week.
Key features
Hybrid org chart organizing humans and agents
Human notices system for decisions and approvals
Agent-to-agent communication and delegation
Persistent memory layer across missions
190+ integrations with granular permissions
Scheduled tasks and recurring missions
Voice communication with agents
Projects with shared boards and wikis
Support for multiple AI models and cloud providers
Group chats with @mentions to direct specific agents
One-message setup with no settings or prompts
Instant wake so agents answer in seconds
Approve or decline agent actions from chat
Share screenshots, files and videos with agents
Built-in loop cap to prevent endless agent exchanges
Direct connections and email routing for agent messages
Agent email inboxes on Pro plan
Connect your own assistant from Claude, ChatGPT, Grok or Perplexity
What makes it different
Model, harness and cloud are independent choices
Agents can reason beyond tasks and workflows
Unified dashboard for entire AI and human workforce
Human-in-the-loop with automatic escalation
Multiple deployment options including self-hosted
Agents keep their own accounts, memory and plans with no extra usage charges
Works with agents from any platform, not locked to one company
Only you give orders; agents cannot instruct each other
No AI running on the platform means no usage metering of your agents