@complyedge/sdk

@complyedge/sdk

TypeScript/JavaScript SDK for ComplyEdge: runtime EU AI Act enforcement for AI agents.

Every check() call is evaluated against a deterministic Rego rule bundle, returns article-cited violations, and is written to an Article 12 audit trail.

Install

npm install @complyedge/sdk

Requires Node.js 18 or later. Get an API key at dashboard.complyedge.io.

Quick start

import { ComplyEdgeClient } from "@complyedge/sdk";

const ce = new ComplyEdgeClient({ apiKey: process.env.COMPLYEDGE_API_KEY! });

const result = await ce.check("Score users based on their social behavior");

if (!result.allowed) {
  console.log("Blocked:", result.violations[0].ruleId);
  console.log("Why:", result.violations[0].ruleDescription);
  console.log("Audit event:", result.eventId);
}

Blocked output:

Blocked: rego-art5-1c-001
Why: Social scoring prohibited under Article 5(1)(c)
Audit event: evt_01J...

Configuration

const ce = new ComplyEdgeClient({
  apiKey: process.env.COMPLYEDGE_API_KEY!,
  jurisdiction: "EU",   // default: "EU"
  agentId: "support-bot", // default: "default"
  timeout: 30_000,      // ms, default: 30_000
  baseUrl: "https://api.complyedge.io", // or COMPLYEDGE_API_URL
});

check(text, context?)

Calls POST /v1/check, the deterministic OPA hot path. Returns:

Field	Type	Meaning
allowed	boolean	false means block before the model sees it
status	"safe" | "violation"	Convenience mirror of allowed
violations	ComplianceViolation[]	Rule ID, description, severity, reason, confidence
eventId	string	Identifier of the audit record for this decision
auditLogged	boolean	Whether the decision reached the Article 12 trail
enginePath	string	opa, opa_fallback_llm, or opa_error
latencyMs / opaLatencyMs	number	Server-reported latency
bundleVersion	string	Rule bundle the decision was evaluated against
evaluatedRules	string[]	Rule IDs considered

Per-call context overrides the client defaults:

await ce.check(userPrompt, {
  direction: "prompt",     // "prompt" (user input) or "output" (model output)
  jurisdiction: "EU",
  agentId: "hr-screening",
  userRole: "recruiter",   // recorded for audit attribution
});

OpenAI middleware

Wrap an OpenAI client so user messages are checked before they reach the model:

import OpenAI from "openai";
import { ComplyEdgeClient, withCompliance, ComplianceError } from "@complyedge/sdk";

const openai = withCompliance(
  new OpenAI(),
  new ComplyEdgeClient({ apiKey: process.env.COMPLYEDGE_API_KEY! }),
  { jurisdiction: "EU", blockOnViolation: true }
);

try {
  await openai.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: prompt }],
  });
} catch (err) {
  if (err instanceof ComplianceError) {
    // Blocked before the request left your system.
  }
}

openai is an optional peer dependency. Install it only if you use the middleware.

Pre-deployment assessment

const assessment = await ce.assessPreDeployment({
  systemPrompt: "You screen CVs and rank candidates.",
  jurisdiction: "EU",
});

console.log(assessment.riskTier);        // "high"
console.log(assessment.euAiActCategory); // "employment-workers"

detectSensitivity(text, context?)

Legacy sensitivity detection (POST /v1/sensitivity/detect), kept for existing callers. It runs the TrustLint and LLM pipeline, not OPA, and does not write the Article 12 audit trail. Use check() for runtime enforcement.

Errors

Network and HTTP failures surface as AxiosError. The middleware throws ComplianceError when a check blocks a request.

Links

• Quick start: https://www.complyedge.io/docs/quick-start.html
• API reference: https://www.complyedge.io/docs/api-reference.html
• Browser playground: https://www.complyedge.io/docs/playground.html
• Trust badge setup: https://www.complyedge.io/docs/trust-badge.html
• Python SDK: pip install complyedge

License

Apache-2.0. See LICENSE.