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.
Free forever for personal use with core features. Plus plan $4/month for cloud sync and early access. Professional $20/month for commercial use with advanced features. Enterprise $100 per seat per month for teams.
Key features
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
AI Staff with persistent memory between sessions
Access to installed AI coding tools (Claude Code, Codex, Cursor, Copilot, Grok)
Run local AI models with one-click setup
Real project access with built-in editor and terminal
Scheduled work that runs remotely while you're away
Multiplayer AI sessions with guest access control
Cloud sync for notes, reports, exhibits and canvases
Windows, macOS, and Linux desktop support
What makes it different
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
AI runs on your computer where your files are, not in the cloud
Staff have persistent identity and memory, not anonymous chat sessions
Full transparency: watch staff reasoning, decisions, tools used and files changed
Works with your existing AI subscriptions or free local models
withHuman
Clairvoyance