N9 Agents Platform
A production-ready AI Agent as a Service platform with persistent memory, self-learning capabilities, and workflow automation.
Persistent Memory
Agents remember user preferences across sessions
Self-Learning
Automatic knowledge acquisition from conversations
RAG System
Semantic search over documents using embeddings
System Architecture
The platform follows a layered architecture with clear separation of concerns.
┌─────────────────────────────────────────────────────────────────┐
│ PRESENTATION LAYER │
│ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │
│ │ Dashboard │ │ Chat UI │ │ Workflow │ │
│ │ (Admin) │ │ (Widget) │ │ Builder │ │
│ └─────────────┘ └─────────────┘ └─────────────┘ │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ API LAYER │
│ /api/chat /api/agents /api/brain /api/workflows │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ SERVICE LAYER │
│ ChatService MemoryService KnowledgeService RAGService │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ REPOSITORY LAYER │
│ AgentRepo ConversationRepo MemoryRepo KnowledgeRepo │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ DATA LAYER │
│ MySQL (ai_agents_db) MySQL (buildhtml) Cloud Storage │
└─────────────────────────────────────────────────────────────────┘
Tech Stack
| Component | Technology | Rationale |
|---|---|---|
| Runtime | Node.js | Non-blocking I/O for real-time chat |
| Framework | Express.js | Lightweight, flexible routing |
| Database | MySQL | ACID compliance, JSON support |
| AI Model | GPT-4.1-mini | Balance of cost and capability |
| Embeddings | text-embedding-3-small | 1536 dims, cost-effective |
Memory System
The three-tier memory architecture enables agents to maintain context and learn from interactions.
┌─────────────────────────────────────────────────────────────────────────┐ │ AGENT INTELLIGENCE │ ├─────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │ │ │ │ │ │ │ │ │ │ │ SHORT-TERM │ │ LONG-TERM │ │ KNOWLEDGE │ │ │ │ MEMORY │ │ MEMORY │ │ BASE │ │ │ │ │ │ │ │ │ │ │ │ Conversation │ │ User Profile │ │ Q&A Pairs │ │ │ │ History │ │ Preferences │ │ Documents │ │ │ │ (Last N msgs) │ │ Facts │ │ (RAG) │ │ │ │ │ │ │ │ │ │ │ │ Scope: Session │ │ Scope: User │ │ Scope: Agent │ │ │ │ TTL: ~30 min │ │ TTL: Permanent │ │ TTL: Permanent │ │ │ │ │ │ │ │ │ │ │ └────────┬────────┘ └────────┬────────┘ └────────┬────────┘ │ │ │ │ │ │ │ └─────────────────────┼─────────────────────┘ │ │ │ │ │ ▼ │ │ ┌────────────────────────┐ │ │ │ CONTEXT BUILDER │ │ │ │ Merges all sources │ │ │ └────────────────────────┘ │ │ │ │ │ ▼ │ │ ┌────────────────────────┐ │ │ │ OPENAI GPT │ │ │ └────────────────────────┘ │ │ │ └─────────────────────────────────────────────────────────────────────────┘
1. Short-Term Memory
Maintains conversation continuity within a session by storing the last N messages.
How It Works
- 1 User sends message
- 2 Message saved to
messagestable with conversation_id - 3 On next request, last N messages retrieved
- 4 History included in OpenAI API call
2. Long-Term Memory
Remembers user-specific information across sessions using a key-value store.
User: "Remember that I prefer morning appointments"
│
▼
┌────────────────────────────────────────────────────────────────┐
│ AI RESPONSE │
│ │
│ Detects memory request and outputs: │
│ {"action":"save","type":"memory", │
│ "title":"appointment_preference", │
│ "content":"prefers morning appointments"} │
└───────────────────────────┬────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────┐
│ MEMORY REPOSITORY │
│ │
│ INSERT INTO memories │
│ (agent_id, session_id, memory_key, memory_value) │
│ VALUES (1, 'user_abc', 'appointment_preference', │
│ 'prefers morning appointments') │
└────────────────────────────────────────────────────────────────┘
│
▼
┌────────────────────────────────────────────────────────────────┐
│ FUTURE CONVERSATIONS │
│ │
│ Context includes: │
│ ## User Information: │
│ - appointment_preference: prefers morning appointments │
└────────────────────────────────────────────────────────────────┘
3. Knowledge Base (Self-Learning)
Builds institutional knowledge from conversations through a training loop.
┌─────────────────────────────────────────────────────────────────────────┐
│ SELF-LEARNING CYCLE │
└─────────────────────────────────────────────────────────────────────────┘
Step 1: User Asks Unknown Question
───────────────────────────────────
User: "What are your business hours?"
│
▼
┌───────────────┐
│ Agent doesn't │────► Log to unanswered_questions
│ know answer │ (question, asked_count)
└───────────────┘
Step 2: Owner Trains Agent
──────────────────────────
┌─────────────────────────────┐
│ TRAINING DASHBOARD │
│ │
│ Pending Questions: │
│ "What are your hours?" │
│ Asked: 15 times │
│ │
│ Owner provides answer: │
│ "Mon-Fri, 9 AM to 5 PM" │
└──────────────┬──────────────┘
│
▼
┌─────────────────────────────┐
│ Add to knowledge base │
│ Q: What are your hours? │
│ A: Mon-Fri, 9 AM to 5 PM │
└─────────────────────────────┘
Step 3: Agent Uses Knowledge
────────────────────────────
Future questions get accurate answers automatically
RAG Pipeline
Retrieval Augmented Generation enables semantic search over uploaded documents.
INGESTION PHASE
───────────────
Document Upload Chunking Embedding
│ │ │
▼ ▼ ▼
┌─────────┐ ┌─────────────────┐ ┌─────────────────┐
│ PDF │ │ Split into │ │ OpenAI API │
│ CSV │ ────────► │ 800-char │ ───────► │ Embeddings │
│ TXT │ │ chunks │ │ (1536 dims) │
└─────────┘ └─────────────────┘ └────────┬────────┘
│
▼
┌───────────────────┐
│ Store in MySQL │
└───────────────────┘
RETRIEVAL PHASE
────────────────
User Query Query Embedding Similarity Search
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ "What is │ │ Embed query │ │ Cosine │
│ the refund │ ────► │ using same │ ─────► │ similarity │
│ policy?" │ │ model │ │ search │
└─────────────┘ └─────────────────┘ └────────┬────────┘
│
▼
┌─────────────────┐
│ Inject into │
│ AI context │
└─────────────────┘
Document Chunking
Documents are split into overlapping chunks to preserve context across boundaries.
800
Chunk Size (chars)
200
Overlap (chars)
1536
Embedding Dims
Overlap ensures concepts spanning chunk boundaries aren't lost during retrieval.
Vector Embeddings
Text is converted to 1536-dimensional vectors that capture semantic meaning.
Input Text:
"We offer a 30-day money-back guarantee on all products"
│
▼
┌──────────────────┐
│ OpenAI API │
│ text-embedding- │
│ 3-small │
└────────┬─────────┘
│
▼
Output Vector (1536 dimensions):
[0.0234, -0.0891, 0.0123, 0.0567, -0.0345, ..., 0.0456]
│ │ │ │ │ │
Dim 1 Dim 2 Dim 3 Dim 4 Dim 5 Dim 1536
Similar texts will have similar vectors (high cosine similarity)
Cosine Similarity Search
Queries are matched against stored chunks using cosine similarity.
Query: "What is your refund policy?"
Chunk about refunds and returns
0.92
Chunk about shipping policies
0.45
Chunk about contact information
0.38
Top matching chunks are injected into the AI prompt as context.
API Reference
Chat Endpoints
POST
/api/chat/:agentSlug/message
{
"session_id": "user_abc123",
"message": "What are your business hours?"
}
Agent Management
GET
/api/agents
List all agents
POST
/api/agents
Create agent
PUT
/api/agents/:id
Update agent
Workflows
POST
/api/workflows/ai-build
Build workflows from natural language
{
"message": "When someone submits a form, send me an email"
}