OpenAI Agents SDK

A tool registry that checks a permission before dispatching a function call, and an agent loop that emits an audit event for every turn without you writing one.

OpenAI Function Calling

Use VorimToolRegistry for permission-checked tool execution with OpenAI chat completions.

import OpenAI from "openai";
import createVorim from "@vorim/sdk";
import { VorimToolRegistry, runAgentLoop } from "@vorim/sdk/integrations/openai";

const vorim = createVorim({ apiKey: "agid_sk_live_..." });
const openai = new OpenAI();

const registry = new VorimToolRegistry({ vorim, agentId: "agid_acme_a1b2c3d4" });

registry.add({
  name: "search_docs",
  description: "Search internal documents",
  parameters: { type: "object", properties: { query: { type: "string" } }, required: ["query"] },
  execute: async ({ query }) => searchDocs(query),
  permission: "agent:read",
});

// Use with chat completions
const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages,
  tools: registry.toOpenAITools(),
});

// Execute tool calls — permission checked + audited automatically
const toolMessages = await registry.executeToolCalls(
  response.choices[0].message.tool_calls ?? []
);

typescript

Need Help?

Book a demo for a walkthrough, or contact us for support. For enterprise needs, reach out at sales@vorim.ai.