Open-source, self-hostable platform for building and governing AI agents across multiple channels
Stage
Not given
Startup
Founded
Not given
2025
Based in
Not given
IN
Pricing model
Freemium
Open source
Pricing
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 to run, fork and build on commercially under Business Source License 1.1; paid hosted plans from $0 to $79 USD
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
Human approval workflows
Multi-channel support (WhatsApp, email, voice, web)
Retrieval and graph memory
Guardrails and governance with budgets
Browser automation
Role-based access control
OpenAPI and Swagger tool import
Agent skill learning
Sealed audit log
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
Runs on laptop, server, or Kubernetes—same images everywhere from release
Complete governance embedded in platform and SDKs with approval, budgets, audit
Open standards: MCP, A2A, AG-UI, OpenTelemetry, OIDC, OpenAPI
Business Source License allows commercial use and forking