Build and run AI agents, teams and workflows without code
The AI assistant who gets work done, before it slips
Stage
Not given
Not given
Founded
Not given
Not given
Based in
BE
Not given
Pricing model
Freemium
Freemium
Pricing
Community: free forever on your own server. Personal: €20/month billed yearly (€240/year) or €24/month billed monthly. Pro: €40.83/month billed yearly (€490/year) or €49/month billed monthly. Business: €165.83/month billed yearly (€1,990/year) or €199/month billed monthly. Enterprise: on quote. All
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
Create workflows with conditions, loops, and human approvals
AI Assistant builds teams from natural language descriptions
Knowledge bases and data tables for agent memory
Prompt Studio for testing and improving agent instructions
VibeApps for conversational user interfaces
Support for multiple AI providers
Community edition runs on your own server with Docker
Hosted cloud workspaces with no installation required
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
No coding required; build with natural language or visual drag-and-drop
Keeps human judgment in control; work returns to people for decisions
Open source Community edition with no time limit or cost
Choose where your data runs: your own server or hosted cloud
AI Assistant generates teams and workflows from plain English descriptions
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