RailCall local runtime: free. RailHub Team: $5 per seat per month. Cloud agents: $5 per trained agent per month. Advanced thinking (overflow): metered against a budget you set, with 500 flows per month included. Storage on hub: $0.25 per GB-month with 5 GB free.
Free during beta
Key features
Studio visual workflow builder with 1,000+ nodes
CLI and terminal-first interface
Ed25519-signed tamper-evident receipts
Human approval airlock for all actions
Autonomous agents that run 24/7
Capacity routing across organization machines
MCP integration with 33 tools
Multi-level human approval workflows
Offline receipt verification
Company-wide stop button
One-click cloud deployment
Support for multiple frameworks (OpenAI Agents SDK, Pydantic AI, LangGraph, CopilotKit)
Built-in AG-UI endpoint for frontend integration
Live session replay and debugging
Streaming text, tool calls and approvals
Durable sessions and message persistence
Serverless human-in-the-loop approvals
Local development environment matching production
Scale to zero during waits
Encrypted secrets management
What makes it different
Entire local runtime free with MIT license, no login required
Cryptographically signed receipts verifiable offline
80% reduction in AI costs compared to top models
No execution counters or machine count limits
Works with any agent framework without framework-specific dependencies
Handles infrastructure complexity like journaling, approvals, and state persistence automatically
Stateless hosting with all conversation state managed on Sectr
Native CopilotKit integration with no additional SDK or event parsing needed
Approvals persist through browser refresh without losing agent progress
RailCall