my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Build a Node.js Companion
#3	description: "Build a JavaScript fitness coach that remembers user goals run after run."
#4	---
#5
#6
#7	You can create a personalized AI Companion using Mem0. This guide will walk you through the necessary steps and provide the complete code to get you started.
#8
#9	## Overview
#10
#11	The Personalized AI Companion leverages Mem0 to retain information across interactions, enabling a tailored learning experience. It creates memories for each user interaction and integrates with OpenAI's GPT models to provide detailed and context-aware responses to user queries.
#12
#13	## Setup
#14
#15	Before you begin, ensure you have Node.js installed and create a new project. Install the required dependencies using npm:
#16
#17	```bash
#18	npm install openai mem0ai
#19	```
#20
#21	## Full Code Example
#22
#23	Below is the complete code to create and interact with an AI Companion using Mem0:
#24
#25	```javascript
#26	import { OpenAI } from 'openai';
#27	import { Memory } from 'mem0ai/oss';
#28	import * as readline from 'readline';
#29
#30	const openaiClient = new OpenAI();
#31	const memory = new Memory();
#32
#33	async function chatWithMemories(message, userId = "default_user") {
#34	const relevantMemories = await memory.search(message, { userId: userId });
#35
#36	const memoriesStr = relevantMemories.results
#37	.map(entry => `- ${entry.memory}`)
#38	.join('\n');
#39
#40	const systemPrompt = `You are a helpful AI. Answer the question based on query and memories.
#41	User Memories:
#42	${memoriesStr}`;
#43
#44	const messages = [
#45	{ role: "system", content: systemPrompt },
#46	{ role: "user", content: message }
#47	];
#48
#49	const response = await openaiClient.chat.completions.create({
#50	model: "gpt-4.1-nano-2025-04-14",
#51	messages: messages
#52	});
#53
#54	const assistantResponse = response.choices[0].message.content \|\| "";
#55
#56	messages.push({ role: "assistant", content: assistantResponse });
#57	await memory.add(messages, { userId: userId });
#58
#59	return assistantResponse;
#60	}
#61
#62	async function main() {
#63	const rl = readline.createInterface({
#64	input: process.stdin,
#65	output: process.stdout
#66	});
#67
#68	console.log("Chat with AI (type 'exit' to quit)");
#69
#70	const askQuestion = () => {
#71	return new Promise((resolve) => {
#72	rl.question("You: ", (input) => {
#73	resolve(input.trim());
#74	});
#75	});
#76	};
#77
#78	try {
#79	while (true) {
#80	const userInput = await askQuestion();
#81
#82	if (userInput.toLowerCase() === 'exit') {
#83	console.log("Goodbye!");
#84	rl.close();
#85	break;
#86	}
#87
#88	const response = await chatWithMemories(userInput, "sample_user");
#89	console.log(`AI: ${response}`);
#90	}
#91	} catch (error) {
#92	console.error("An error occurred:", error);
#93	rl.close();
#94	}
#95	}
#96
#97	main().catch(console.error);
#98	```
#99
#100	### Key Components
#101
#102	1. Initialization
#103	- The code initializes both OpenAI and Mem0 Memory clients
#104	- Uses Node.js's built-in readline module for command-line interaction
#105
#106	2. Memory Management (chatWithMemories function)
#107	- Retrieves relevant memories using Mem0's search functionality
#108	- Constructs a system prompt that includes past memories
#109	- Makes API calls to OpenAI for generating responses
#110	- Stores new interactions in memory
#111
#112	3. Interactive Chat Interface (main function)
#113	- Creates a command-line interface for user interaction
#114	- Handles user input and displays AI responses
#115	- Includes graceful exit functionality
#116
#117	### Environment Setup
#118
#119	Make sure to set up your environment variables:
#120	```bash
#121	export OPENAI_API_KEY=your_api_key
#122	```
#123
#124	### Conclusion
#125
#126	This implementation demonstrates how to create an AI Companion that maintains context across conversations using Mem0's memory capabilities. The system automatically stores and retrieves relevant information, creating a more personalized and context-aware interaction experience.
#127
#128	As users interact with the system, Mem0's memory system continuously learns and adapts, making future responses more relevant and personalized. This setup is ideal for creating long-term learning AI assistants that can maintain context and provide increasingly personalized responses over time.
#129
#130	---
#131
#132	<CardGroup cols={2}>
#133	<Card title="Partition Memories by Entity" icon="layers" href="/cookbooks/essentials/entity-partitioning-playbook">
#134	Separate user, agent, and session context to keep your companion consistent.
#135	</Card>
#136	<Card title="Quickstart Demo with Mem0" icon="rocket" href="/cookbooks/companions/quickstart-demo">
#137	Run the full showcase app to see memory-powered companions in action.
#138	</Card>
#139	</CardGroup>
#140

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public