@frontegg/ai-sdk NPM

Frontegg AI Agents SDK

The Frontegg AI Agents SDK provides AI Agent developers with tools and utilities to easily empower AI agents within their applications. This SDK seamlessly integrates with the Frontegg platform, enabling advanced tool authentication, authorization, and identity management capabilities for AI Agents.

Features

Secure integration with Frontegg authentication
Easy integration with Frontegg built-in and 3rd party application tools
User identity context for agent throught Frontegg's identity platform
Seamless integration with Langchain AI applications and agents

🚀 Prerequisites

Ensure that your environment meets the following requirements:

Node.js: Version 18.16.0 or later
TypeScript: Version 5.7.2 or later
A working LangChain project with agent implementation
Access to a Frontegg tenant and registered application credentials

Installation

npm install @frontegg/ai-sdk
# or
yarn add @frontegg/ai-sdk

Quick Start

SDK Configuration

Initialize the Frontegg AI client to connect with your tenant environment:

// frontegg.config.ts
import { Environment, FronteggAiClient } from '@frontegg/ai-sdk';

export const fronteggClient = await FronteggAiClient.getInstance({
  agentId: process.env.FRONTEGG_AGENT_ID!,
  clientId: process.env.FRONTEGG_CLIENT_ID!,
  clientSecret: process.env.FRONTEGG_CLIENT_SECRET!,
  environment: Environment.EU,
});

Dynamic Tool Integration with User Context

Fetch user-specific tools from Frontegg and dynamically construct a LangChain agent:

public async processRequest(request: string, userJwt: string): Promise<any> {
  if (!this.fronteggAiClient) {
    throw new Error('Frontegg client not initialized');
  }

  await this.fronteggAiClient.setUserContextByJWT(userJwt);
  const tools = await this.fronteggAiClient.getToolsAsLangchainTools();

  const messages = [
    {
      role: 'system',
      content: this.fronteggAiClient.addUserContextToSystemPrompt(this.systemMessage),
    },
    ...this.conversationHistory,
    new MessagesPlaceholder('agent_scratchpad'),
  ];

  const prompt = ChatPromptTemplate.fromMessages(messages);

  const openAIFunctionsAgent = await createOpenAIFunctionsAgent({
    llm: this.model as any,
    tools: tools as any,
    prompt: prompt as any,
  });

  this.agent = new AgentExecutor({
    agent: openAIFunctionsAgent as any,
    tools: tools as any,
    verbose: true,
  });

  const result = await this.agent.invoke({ input: request });

  return result;
}