Loading...
Loading...
Everything you need to integrate AI agent governance, content protection, and trust certification into your applications.
import { DRD } from '@drd/sdk';
const drd = new DRD({
apiKey: process.env.DRD_API_KEY,
});
// Check if action is allowed
const result = await drd.guard('send_email', {
to: 'user@example.com',
subject: 'Weekly report',
});
if (result.allowed) {
await sendEmail(result.context);
await drd.report('email.sent', {
to: 'user@example.com',
subject: 'Weekly report',
});
}Install with npm install @drd/sdk
Create your account, register your first agent, and run a policy check in under 5 minutes.
Step-by-step walkthrough from zero to a running agent with trust scoring in minutes.
Complete REST API documentation with request/response schemas, error codes, and authentication.
Interactive API explorer — test endpoints live with your own API key and see real responses.
Download the OpenAPI 3.1 specification for code generation, Postman collections, and CI validation.
Install @drd/sdk, configure your agent, and integrate guard(), report(), and waitForApproval().
Register agents, define policies, set up enforcement tiers, and configure approval workflows.
Cedar-style policy authorization with pluggable backends, versioned rulesets, and dry-run evaluation.
Tiered enforcement actions from warnings to kill switches, with escalation rules and appeal workflows.
Fingerprinting, watermarking, C2PA provenance, and Merkle tree anchoring for your content.
Earn Bronze, Silver, Gold, or Government trust badges. Embed verifiable credentials in your agent.
Dashboard auth via Clerk, API key management, and Ed25519 JWT tokens for SDK access.
Subscribe to events, configure webhook endpoints, and process HMAC-signed deliveries.
Understand the 0-100 trust score, scoring factors, history tracking, and SDK integration.
Create monitoring rules, configure alerts, activate kill switches, and manage agent oversight.
Submit content for AI-powered deepfake analysis across face-swap, voice clone, and synthetic media.
Create or join federations for cross-org trust signals, collective enforcement, and shared governance.
Set up AI-powered monitors for brand mentions, content scanning, and automated threat detection.
Create and manage content licenses with single-use, subscription, and royalty-based models.
Immutable hash-chained audit trails with Merkle tree anchoring, CQRS read models, and event replay.
Cross-organization trust scoring through privacy-preserving aggregation and mTLS federation endpoints.
C2PA content provenance, deepfake detection, training data verification, and EU AI Act compliance automation.
W3C Verifiable Credentials v2.0 and DIDs for AI agent identity with Ed25519 signatures and badge tiers.
Multi-agent coordination with consensus voting, trust-weighted decisions, and swarm governance policies.
Manage regulatory frameworks, schedule audits, track compliance scores, and automate remediation.
Submit KYC verification for AI agents with basic, enhanced, and enterprise verification levels.
File DMCA takedown requests, scan training data for copyright violations, and manage compliance.