Loading...
Loading...
Create your account, register your first agent, and run a policy check in under 5 minutes.
Step 1
Sign up at drd.io/signup using your email, GitHub, or Google account. Once signed in, you'll land on your dashboard.
Step 2
Workspaces isolate your agents, policies, and events. Create one from the dashboard or via the API.
curl -X POST https://api.drd.io/api/v1/workspaces \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"name": "my-workspace", "slug": "my-workspace"}'Step 3
Every AI agent that interacts with DRD needs to be registered. This gives it an identity, API key, and trust score.
curl -X POST https://api.drd.io/api/v1/agents \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "email-bot",
"description": "Sends weekly digest emails",
"type": "automation"
}'Step 4
Install the @drd/sdk package from npm to integrate governance checks into your agent.
npm install @drd/sdkStep 5
Use guard() to check if an action is allowed, then report() to log the event and build your agent's reputation.
import { DRD } from '@drd/sdk';
const drd = new DRD({ apiKey: process.env.DRD_API_KEY });
// Check if the action is allowed
const result = await drd.guard('send_email', {
to: '[email protected]',
subject: 'Weekly report',
});
if (result.allowed) {
await sendEmail(result.context);
await drd.report('email.sent', { to: '[email protected]' });
}
await drd.shutdown();API Reference
Full endpoint documentation with request/response schemas
Explore endpointsSDK Guide
Deep dive into guard(), report(), and error handling
Read the guideAgent Governance
Policies, enforcement tiers, and approval workflows
Learn moreTrust Badges
Earn "PROTECTED BY DRD" certification for your agents
Get certified