Control what your AI can do
One function at a time
Secure your LLM tools with deterministic guardrails and function-level authorization. One decorator, instant security. Zero infrastructure.
From Complex to Simple
Replace hundreds of lines of authorization logic with a single decorator.
Built for Production AI Systems
Runtime-optimized authorization that identifies security issues at the code level, not just endpoints.
Just add @d2_guard to your functions. Extremely simple code that replaces hundreds of lines of auth logic.
Define all authorization logic in YAML/JSON policy files—no code changes needed. Updates propagate in under a minute. Policy validation catches typos before they reach production.
Three layers of deterministic guardrails: RBAC controls who can call what, input/output validation, and sequence enforcement prevents multi-step attacks.
Predictable, rule-based security controls. Input validation constrains function arguments. Output sanitization removes PII. All decisions are deterministic and auditable—no probabilistic judgments.
Built for high-performance production systems with minimal overhead and intelligent caching.
Every authorization decision emits telemetry. Track denials, sequence violations, and sanitization actions. OpenTelemetry integration for production monitoring and debugging.
Your Control Center
View telemetry, edit policies, download events, and more.
Event Monitoring
Track every authorization decision in real-time
Analytics & Insights
Visualize patterns and performance metrics
Visual Policy Editor
Create and edit authorization policies easily
API Token Management
Manage tokens and authentication securely
Simple, Transparent Pricing
Start free with local mode. Scale to cloud for production with enterprise features.
Per month
Per month
For large organizations
All plans include:
Ready to Secure Your AI Agents?
Tell us about your use case and we'll help you get started.