Runtime security layer that stops risky AI actions before they execute
Interactive worlds for people and AI to build, learn and solve problems together
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Free
Pricing
Free plan: Local Guard runtime with real-time approval prompts and local audit log. Solo $4.99/mo: adds 2 cloud-connected devices and 30-day cloud retention. Pro $15/mo: adds 5 cloud-connected devices, 180-day retention, and policy versioning. Team $30/seat/mo: up to 25 cloud-connected devices, 365-
Not given
Key features
Surface-specific pre-action interception
Policy routing with allow, observe, ask, and block outcomes
Local review and evidence workflows
MCP, skill, plugin, and package inspection
Layered local and team policy
Open source runtime under Apache-2.0
Offline local protection without cloud connectivity
Continuous GitHub leaked-secret monitoring
Decision audit trail and export
Support for multiple AI coding agents
Photo to brick set conversion with 3D preview and parts list
Workbench for collaborative brick-by-brick editing
MCP server integration with Claude Code, Codex, Cursor and more
Build structure checking and validation
OAuth sign-in with no token storage
Offline build access with local browser storage
Export digital manuals and wanted parts lists
Interactive environments for AI training
Consent-based human demonstration recording
What makes it different
Open-source core runtime runs locally without cloud requirement
Protects against secrets, destructive commands, prompt injection, and supply chain attacks
No source code or secrets uploaded; decisions stored as redacted summaries
Checked outcomes - part connections and build validity are verified by software before delivery
Real objects from photos - converts pictures into buildable brick sets with actual parts that exist
People and AI work on the same design simultaneously within the workbench
Measurable AI learning with transfer testing across different worlds