Reference architectures for Lindy AI integrations. Use when designing systems, planning architecture, or implementing production patterns. Trigger with phrases like "lindy architecture", "lindy design", "lindy system design", "lindy patterns".
Installation
Details
Usage
After installing, this skill will be available to your AI coding assistant.
Verify installation:
skills listSkill Instructions
name: lindy-reference-architecture description: | Reference architectures for Lindy AI integrations. Use when designing systems, planning architecture, or implementing production patterns. Trigger with phrases like "lindy architecture", "lindy design", "lindy system design", "lindy patterns". allowed-tools: Read, Write, Edit version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io
Lindy Reference Architecture
Overview
Production-ready reference architectures for Lindy AI integrations.
Prerequisites
- Understanding of system design principles
- Familiarity with cloud services
- Production requirements defined
Architecture Patterns
Pattern 1: Basic Integration
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Client │────▶│ Backend │────▶│ Lindy AI │
│ (React) │◀────│ (Node.js) │◀────│ API │
└─────────────┘ └─────────────┘ └─────────────┘
// Simple backend integration
import express from 'express';
import { Lindy } from '@lindy-ai/sdk';
const app = express();
const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });
app.post('/api/chat', async (req, res) => {
const { message, agentId } = req.body;
const result = await lindy.agents.run(agentId, { input: message });
res.json({ response: result.output });
});
Pattern 2: Event-Driven Architecture
┌──────────────────────────────────────────────────────────┐
│ Event Bus (Redis/SQS) │
└────┬─────────────────┬─────────────────┬────────────────┘
│ │ │
▼ ▼ ▼
┌─────────┐ ┌─────────┐ ┌─────────┐
│ Worker │ │ Worker │ │ Worker │
│ (Agent) │ │ (Agent) │ │ (Agent) │
└────┬────┘ └────┬────┘ └────┬────┘
│ │ │
└────────────────┼────────────────┘
▼
┌─────────────┐
│ Lindy AI │
│ API │
└─────────────┘
// Event-driven worker
import { Queue } from 'bullmq';
import { Lindy } from '@lindy-ai/sdk';
const lindy = new Lindy({ apiKey: process.env.LINDY_API_KEY });
const queue = new Queue('lindy-tasks');
// Producer
async function enqueueTask(agentId: string, input: string) {
await queue.add('run-agent', { agentId, input });
}
// Consumer
const worker = new Worker('lindy-tasks', async (job) => {
const { agentId, input } = job.data;
const result = await lindy.agents.run(agentId, { input });
// Emit result event
await eventBus.publish('agent.completed', {
jobId: job.id,
result: result.output,
});
});
Pattern 3: Multi-Agent Orchestration
┌─────────────────┐
│ Orchestrator │
│ Agent │
└────────┬────────┘
│
┌─────────────────┼─────────────────┐
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Research │ │ Analysis │ │ Writing │
│ Agent │ │ Agent │ │ Agent │
└─────────────┘ └─────────────┘ └─────────────┘
// Multi-agent orchestrator
class AgentOrchestrator {
private lindy: Lindy;
private agents: Record<string, string> = {
research: 'agt_research',
analysis: 'agt_analysis',
writing: 'agt_writing',
orchestrator: 'agt_orchestrator',
};
async execute(task: string): Promise<string> {
// Step 1: Orchestrator plans the work
const plan = await this.lindy.agents.run(this.agents.orchestrator, {
input: `Plan steps for: ${task}`,
});
// Step 2: Execute each step
const steps = JSON.parse(plan.output);
const results: string[] = [];
for (const step of steps) {
const result = await this.lindy.agents.run(
this.agents[step.agent],
{ input: step.task }
);
results.push(result.output);
}
// Step 3: Synthesize results
const synthesis = await this.lindy.agents.run(this.agents.orchestrator, {
input: `Synthesize: ${results.join('\n')}`,
});
return synthesis.output;
}
}
Pattern 4: High-Availability Setup
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Load │────▶│ App │────▶│ Lindy │
│ Balancer │ │ Server 1 │ │ Primary │
└─────────────┘ └─────────────┘ └──────┬──────┘
│
┌─────────────┐ ┌──────▼──────┐
│ App │────▶│ Lindy │
│ Server 2 │ │ Fallback │
└─────────────┘ └─────────────┘
│
┌─────────────┐ ┌─────────────┐ │
│ Cache │◀────│ Shared │◀───────────┘
│ (Redis) │ │ State │
└─────────────┘ └─────────────┘
// HA client with failover
class HALindyClient {
private primary: Lindy;
private fallback: Lindy;
private cache: Redis;
async run(agentId: string, input: string) {
// Check cache first
const cached = await this.cache.get(`${agentId}:${input}`);
if (cached) return JSON.parse(cached);
try {
// Try primary
const result = await this.primary.agents.run(agentId, { input });
await this.cache.setex(`${agentId}:${input}`, 300, JSON.stringify(result));
return result;
} catch (error) {
// Fallback
console.warn('Primary failed, using fallback');
return this.fallback.agents.run(agentId, { input });
}
}
}
Output
- Architecture diagrams
- Implementation patterns
- HA/failover strategies
- Multi-agent orchestration
Error Handling
| Pattern | Failure Mode | Recovery |
|---|---|---|
| Basic | API error | Retry with backoff |
| Event-driven | Worker crash | Queue retry |
| Multi-agent | Step failure | Skip or fallback |
| HA | Primary down | Automatic failover |
Resources
Next Steps
Proceed to Flagship tier skills for enterprise features.
More by jeremylongshore
View allRabbitmq Queue Setup - Auto-activating skill for Backend Development. Triggers on: rabbitmq queue setup, rabbitmq queue setup Part of the Backend Development skill category.
evaluating-machine-learning-models: This skill allows Claude to evaluate machine learning models using a comprehensive suite of metrics. It should be used when the user requests model performance analysis, validation, or testing. Claude can use this skill to assess model accuracy, precision, recall, F1-score, and other relevant metrics. Trigger this skill when the user mentions "evaluate model", "model performance", "testing metrics", "validation results", or requests a comprehensive "model evaluation".
building-neural-networks: This skill allows Claude to construct and configure neural network architectures using the neural-network-builder plugin. It should be used when the user requests the creation of a new neural network, modification of an existing one, or assistance with defining the layers, parameters, and training process. The skill is triggered by requests involving terms like "build a neural network," "define network architecture," "configure layers," or specific mentions of neural network types (e.g., "CNN," "RNN," "transformer").
Oauth Callback Handler - Auto-activating skill for API Integration. Triggers on: oauth callback handler, oauth callback handler Part of the API Integration skill category.
