| What it does | Self-hostable AI workflow automation platform
| The approval layer for AI agents
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Community: Free (1 user, 10 workflows, no license key); Starter: $19/month (3 users, 25 workflows, 3 activations); Pro: $59/month (10 users, 150 workflows, 10 activations); Unlimited: $149/month (25 users, unlimited workflows within fair use, 25 activations); Enterprise: Custom Quote
| Open Source: free and self-hosted. Free: $0/month hosted plan with up to 5 members. Scale: $20 per user per month. Enterprise: Custom annual contract.
|
|---|
| Key features | - Conversations triggered from chat, forms, schedules, or events with model, tool, and API calls
- Graph and YAML workflow control with typed contracts and version control
- Reusable actions, LLM calls, capability bindings, and external system connections
- Managed memory, retrieval-augmented context, and MCP integration
- Human review points with conditionals, loops, segmentation, and live handoff
- Multilingual assistants across web, messaging, social, and custom channels
- Source-available codebase with full infrastructure control
- No message volume or workflow execution billing
- Deployment across on-premise or cloud infrastructure
- GDPR and compliance support with self-managed storage and audit trails
| - Tool call interception for all agent frameworks
- Automatic approval rules to prevent fatigue
- AI judge for complex rule evaluation
- Works with LangGraph, CrewAI, Mastra, Claude Agent SDK and more
- Open Agent Approval Protocol for framework independence
- Self-hosted or cloud-hosted deployment options
- Custom permission policies and organization controls
|
|---|
| What makes it different | - Complete self-hosting and data control without third-party data handling
- Fair Core License permits use for any purpose except competing use
- Predictable license-key pricing with no message or execution metering
- One runtime connects conversations, actions, memory, and tools across multiple channels
- Custom actions, channels, and extensions for enterprise deployments
| - Framework-agnostic: works with any AI agent through the open Agent Approval Protocol
- No vendor lock-in: open source spec and SDKs let you swap providers without rewriting agents
- Comprehensive audit trail for accountability and compliance
- Meets reviewers where they work with multi-platform notifications
- Policy-based routing to eliminate approval bottlenecks
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 40 ● no change since last check | 30 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 20 | 6 |
|---|
| Citation Flow (Majestic) | 28 | 28 |
|---|
| Referring domains (Majestic) | 275 | 48 |
|---|
withHuman