Chat Memory App (Atulya Cloud)

A demo chat application with persistent per-user memory powered by Atulya Cloud. Supports OpenAI or Groq as the LLM provider. No local Atulya server required.

Features​

• 🧠 Persistent Memory: Each user gets their own memory bank that remembers conversations
• ☁️ Atulya Cloud: Memory stored in the cloud — no Docker setup needed
• 🔀 Selectable LLM: Choose between OpenAI (GPT-4o) or Groq (Qwen 32B)
• 🎯 Per-User Context: Isolated memory per user with automatic context retrieval
• 💬 Real-time Chat: Instant responses with memory-augmented context

Setup​

1. Get API Keys​

• Atulya — Sign up at https://atulya.eightengine.com
• OpenAI — https://platform.openai.com/api-keys
• Groq (alternative) — Free at https://console.groq.com/home

2. Configure Environment​

Edit .env.local with your API keys and preferred provider:

# LLM Provider: "openai" or "groq"
LLM_PROVIDER=openai

# OpenAI (required if LLM_PROVIDER=openai)
OPENAI_API_KEY=sk-your-key-here

# Groq (required if LLM_PROVIDER=groq)
GROQ_API_KEY=gsk_your-key-here

# Atulya Cloud
ATULYA_API_URL=https://api.atulya.eightengine.com
ATULYA_API_KEY=hsk_your-key-here

You can also override the model with LLM_MODEL (defaults to gpt-4o for OpenAI, qwen/qwen3-32b for Groq).

3. Install Dependencies​

npm install

4. Run the App​

npm run dev

Open http://localhost:3000 in your browser.

How It Works​

1. User Identity: Each browser session gets a unique user ID
2. Memory Bank Creation: First message creates a personal memory bank in Atulya Cloud
3. Context Retrieval: Before responding, relevant memories are recalled
4. Memory Augmented Response: LLM generates responses with memory context
5. Conversation Storage: Each conversation is retained for future context

Architecture​

User Message
     ↓
Next.js API Route (/api/chat)
     ↓
Atulya Cloud recall() → Get relevant memories
     ↓
OpenAI or Groq → Generate response with memory context
     ↓
Atulya Cloud retain() → Store conversation
     ↓
Response to User

Memory Bank Structure​

Each user gets their own isolated memory bank with:

• Name: "Chat Memory for [userId]"
• Background: Conversational AI assistant context
• Disposition: Empathetic (4), Low Skepticism (2), Balanced Literalism (3)

Try It Out​

1. First Conversation: Tell the assistant about yourself

   • "Hi! I'm a software engineer from San Francisco. I love Python and machine learning."

2. Second Conversation: Ask what it remembers

   • "What do you know about me?"
   • "What programming languages do I like?"

3. Context Building: Continue sharing preferences

   • "I prefer VS Code over other editors"
   • "I'm working on a React project"

4. Memory Verification: Log in to the Atulya dashboard to see stored memories

Configuration​