The Enterprise Agent Build & Runtime for the work your business runs on
Open-source AI infrastructure you self-host on your own hardware with your own keys
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free plan with 50 workflow executions per month and visual editor. Enterprise plan with custom pricing includes governance, dedicated VPC, and comprehensive support.
Self-host: $0 (open source, MIT-licensed). Service and Enterprise tiers available on contact for integration and custom development work.
Key features
Visual editor and AI copilot
No-code visual editor, exportable to Python
Code-first API built for total control
Real-time tracing of every LLM call, tool call, and memory read
RBAC and audit with immutable audit trails and Enterprise IAM
Human-in-the-loop approval gates and intervention during execution
Runtime hooks inject PII redaction and policy checks
Automated and human-guided training for continuous improvement
Multi-LLM testing for model swapping at runtime
GitHub integration
Provider routing with LiteLLM
What makes it different
Agentic use case generator powered by billions of agent runs
Intelligently guided by 700k agent workflow patterns
Control Plane sits in execution path ensuring every agent interaction is observable, compliant, and reversible
Every production run turns into training data to sharpen accuracy and save money
Complete ownership: your keys, hardware, data and audit logs stay under your control
No vendor lock-in: compose individual modules with your existing stack rather than replacing it
Full transparency: MIT-licensed, publicly developed on GitHub with open issues, PRs and commit history
Every request traceable: one ID threads through all services with full audit logging