AI agents for specific business functions that rehearse tasks as test runs before execution
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
DE
Pricing model
Freemium
Paid
Pricing
Free: $0 with 10 agents, 2 parallel runs, 2 GB storage. Start: $20/month with 100 agents, 5 parallel runs, 10 GB storage. Plus: $50/month with 300 agents, 12 parallel runs, 50 GB storage. Pro: $200/month with 1000 agents, 30 parallel runs, 250 GB storage. On paid plans, model usage billed at true pr
Roles range from € 99 to € 499 per month excluding VAT, with included monthly tasks varying by role: Administrative Assistant and Association Secretary at € 99/mo (40-45 tasks); Secretary at € 109/mo (50 tasks); Process Documentation and Planner at € 129/mo (15-40 tasks); Customer Service at € 229/m
Key features
Hierarchical agent trees with parent-child delegation and coordination
Container-isolated agent environments with Linux shell and persistent filesystem
Persistent agent memory and context between runs
Cron-based scheduled execution with overlap handling
Shared /shared folder for cross-agent file collaboration
Support for 30+ AI models from multiple providers
Web IDE with terminal access and five editor themes
Static site dashboards built and maintained by agents
Voice input and file attachment support
Pre-built roles from a catalogue (31 roles)
Fingerprint verification on approval (SHA-256)
Full audit trail of proposals, test runs and approvals
Integration with 12+ pre-connected services
Custom REST API and MCP server connections
Servers in Germany within EU
AI Act compliance file (limited risk classification)
What makes it different
Agentic tree structure where agents collaborate and share context unlike stateless tools
Fully isolated Linux containers for each agent with persistent filesystems
Persistent memory and context continuity across scheduled runs
Mix and match 30+ AI models freely within the same team
Pricing per fleet rather than per seat or per token overage
Test runs show actual outcomes with no side effects before real execution
No automatic approvals—every proposal requires explicit human approval
Approved test run and execution count together as one task, not two
Declined proposals are free and don't count against quota
Taurus
Stilops