lindy-sdk-patterns

Lindy AI SDK best practices and common patterns.Use when learning SDK patterns, optimizing API usage,or implementing advanced agent features.Trigger with phrases like "lindy SDK patterns", "lindy best practices","lindy API patterns", "lindy code patterns".

📖 中文导读:Lindy AI SDK best practices and common patterns.Use when learning SDK patterns, optimizing API usage,or implementing advanced agent features.Trigger with phrases like "lindy SDK patterns", "lindy best practices","lindy API patterns", "lindy code patterns". 以下正文为该技能的原始 SKILL.md 内容(英文),上方安装命令可直接使用。

name: lindy-sdk-patterns description: | Lindy AI SDK best practices and common patterns. Use when learning SDK patterns, optimizing API usage, or implementing advanced agent features. Trigger with phrases like "lindy SDK patterns", "lindy best practices", "lindy API patterns", "lindy code patterns". allowed-tools: Read, Write, Edit version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io

Lindy SDK Patterns

Overview

Essential SDK patterns and best practices for Lindy AI agent development.

Prerequisites

  • Completed lindy-install-auth setup
  • Basic understanding of async/await
  • Familiarity with TypeScript

Instructions

Pattern 1: Client Singleton

// lib/lindy.ts
import { Lindy } from '@lindy-ai/sdk';

let client: Lindy | null = null;

export function getLindyClient(): Lindy {
  if (!client) {
    client = new Lindy({
      apiKey: process.env.LINDY_API_KEY!,
      timeout: 30000,
    });
  }
  return client;
}

Pattern 2: Agent Factory

// agents/factory.ts
import { getLindyClient } from '../lib/lindy';

interface AgentConfig {
  name: string;
  instructions: string;
  tools?: string[];
}

export async function createAgent(config: AgentConfig) {
  const lindy = getLindyClient();

  const agent = await lindy.agents.create({
    name: config.name,
    instructions: config.instructions,
    tools: config.tools || [],
  });

  return agent;
}

Pattern 3: Retry with Backoff

async function runWithRetry<T>(
  fn: () => Promise<T>,
  maxRetries = 3
): Promise<T> {
  for (let i = 0; i < maxRetries; i++) {
    try {
      return await fn();
    } catch (error: any) {
      if (error.status === 429 && i < maxRetries - 1) {
        await new Promise(r => setTimeout(r, Math.pow(2, i) * 1000));
        continue;
      }
      throw error;
    }
  }
  throw new Error('Max retries exceeded');
}

Pattern 4: Streaming Responses

async function streamAgentResponse(agentId: string, input: string) {
  const lindy = getLindyClient();

  const stream = await lindy.agents.runStream(agentId, { input });

  for await (const chunk of stream) {
    process.stdout.write(chunk.delta);
  }
  console.log(); // newline
}

Output

  • Reusable client singleton pattern
  • Agent factory for consistent creation
  • Robust error handling with retries
  • Streaming support for real-time output

Error Handling

Pattern Use Case Benefit
Singleton Connection reuse Reduced overhead
Factory Agent creation Consistency
Retry Rate limits Reliability
Streaming Long responses Better UX

Examples

Complete Agent Service

// services/agent-service.ts
import { getLindyClient } from '../lib/lindy';

export class AgentService {
  private lindy = getLindyClient();

  async createAndRun(name: string, instructions: string, input: string) {
    const agent = await this.lindy.agents.create({ name, instructions });
    const result = await this.lindy.agents.run(agent.id, { input });
    return { agent, result };
  }

  async listAgents() {
    return this.lindy.agents.list();
  }

  async deleteAgent(id: string) {
    return this.lindy.agents.delete(id);
  }
}

Resources

Next Steps

Proceed to lindy-core-workflow-a for agent creation workflows.