OpenAI Agents SDK

Connect OpenAI Agents SDK to DashClaw and get your first governed action into /decisions in under 20 minutes.

Instance URL detected: https://your-dashclaw-instance.example.com

Deploy DashClaw

Get a running instance. Click the Vercel deploy button or run locally.

Already have an instance? Skip to Step 2.

Install the DashClaw SDK

Add the DashClaw Node.js SDK to your agent project.

Terminal

npm install dashclaw dotenv

Set environment variables

Create a .env file in your agent project root.

.env

DASHCLAW_BASE_URL=https://your-dashclaw-instance.example.com
DASHCLAW_API_KEY=oc_live_...

Put the export callback behind runGoverned

Pass the exact export act and callback to runGoverned. It binds current policy, one persisted action, approval, one execution claim, and outcome reporting.

governed-agent.js

import 'dotenv/config';
import { DashClaw } from 'dashclaw';

process.on('unhandledRejection', (reason) => {
  console.error('Unhandled Rejection:', reason);
  process.exit(1);
});

const claw = new DashClaw({
  baseUrl: process.env.DASHCLAW_BASE_URL,
  apiKey: process.env.DASHCLAW_API_KEY,
  agentId: 'my-openai-agent',
});

const result = await claw.runGoverned(
  { kind: 'file', file: { path: 'report.csv' } },
  {
    action_type: 'data_export',
    declared_goal: 'Export customer report to CSV',
    risk_score: 45,
    systems_touched: ['customer_database'],
  },
  async () => 'Exported 150 customer records to report.csv',
);

console.log(result);

The repository OpenAI Agents example uses an older cooperative guard-and-record loop around simulated data. Use this runGoverned pattern when the callback can cause a real effect.

Run the governed agent

Execute your agent and watch the governance flow.

Terminal

node --env-file=.env governed-agent.js

See the result in DashClaw

Open your DashClaw dashboard to confirm the action was recorded.

Go to /decisions: you should see your action in the ledger with action_type 'data_export', status 'completed', and the output summary you provided.

What success looks like

Go to /decisions: you should see your action in the ledger with action_type 'data_export', agent_id 'my-openai-agent', and status 'completed'.

Navigate to /decisions in your DashClaw instance. Your action should appear in the ledger within seconds of the agent run.

Governance as Code

guardrails.yml is a policy-as-code template. Import it into your instance — POST the YAML to /api/policies/import or call the Python SDK's import_policies — and DashClaw evaluates these rules at the guard step before any action executes.

guardrails.yml

version: 1
project: my-openai-agent
description: >
  Governance policy for an OpenAI Agents SDK data agent.
  High-risk deletions require approval. Reads are auto-allowed.

policies:
  - id: approve_deletions
    description: Require human approval for any delete operation
    applies_to:
      tools:
        - delete_records
        - drop_table
    rule:
      require: approval

  - id: auto_allow_reads
    description: Read operations are low risk
    applies_to:
      tools:
        - scan_for_pii
        - list_records
    rule:
      allow: true