Why Memory?

Every AI has a problem: it forgets. Here's why memory matters and how Tensorheart solves it.

The Problem

LLMs have a context window—a limit on how much text they can process at once. When you're building an AI agent or chatbot, this creates real challenges:

Your Agent's Reality:
┌─────────────────────────────────────────┐
│  Context Window: 128K tokens            │
│  ┌─────────────────────────────────┐    │
│  │ System prompt          2K       │    │
│  │ Conversation history   50K      │    │
│  │ Retrieved documents    70K      │    │
│  │ Available for response 6K       │    │ ← Not much room left
│  └─────────────────────────────────┘    │
└─────────────────────────────────────────┘

You could just stuff everything into the context, but:

• It's expensive — More tokens = more cost
• It's slow — Larger contexts take longer to process
• It hurts quality — Irrelevant information confuses the model

The Solution

Tensorheart Memory acts as your AI's intelligent memory system. Instead of dumping everything into context, it:

1. Stores information when you learn it
2. Retrieves only what's relevant to each query
3. Reduces context size automatically

Traditional Approach:              With Memory:
┌──────────────────┐              ┌──────────────────┐
│ Send everything  │              │ Query: "What's   │
│ 50,000 tokens    │              │ the user's name?"│
│ $0.15 per query  │              │                  │
│ Slow, noisy      │              │ ↓ Find relevant  │
└──────────────────┘              │                  │
                                  │ Return: "User's  │
                                  │ name is Sarah"   │
                                  │ 50 tokens, $0.02 │
                                  └──────────────────┘

How It Works

You store information, then query for what's relevant:

Query: "What programming language does the user prefer?"

Memories:                              Returned:
├─ "User prefers Python"               ✓ (relevant)
├─ "User works at Netflix"             ✗ (not relevant)
├─ "User likes dark mode"              ✗ (not relevant)
└─ "User mentioned JavaScript once"    ✓ (relevant)

Only the relevant memories are returned for your LLM to use.

Why Tensorheart Memory?

Intelligent Retrieval

Memory returns what's actually relevant to your query—not just what's semantically similar.

Query	What You Get
"user's email"	"User's email is john@acme.com"
"project deadline"	"Project due March 15"

Cost-Effective

By sending only relevant context, you dramatically reduce token usage:

Approach	Cost per Query
Full context (50K tokens)	~$0.15
Memory-filtered (2K tokens)	~$0.02
Savings	~87%

Works With Any LLM

Memory is provider-agnostic. Query memories and use them with OpenAI, Anthropic, local models, or any API:

# Query memories, then use with any LLM you choose
curl -X POST https://memoryapi.tensorheart.com/v1/query \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"context": "What does the user prefer?"}'

{
  "success": true,
  "data": {
    "memories": [
      {"id": "mem_abc", "text": "User prefers Python", "relevance_score": 0.91}
    ],
    "query_context": "What does the user prefer?",
    "total_memories_searched": 25
  }
}

Real-World Impact

Here's what Memory enables:

Use Case	Without Memory	With Memory
Customer Support Bot	Forgets user history	Remembers past issues, preferences
Personal Assistant	Asks same questions	Knows your schedule, habits
Code Assistant	Searches entire codebase	Finds relevant functions instantly
Sales AI	Generic responses	Personalized based on CRM data

Quick Example

Store some facts:

curl -X POST https://memoryapi.tensorheart.com/v1/memories \
  -H "Authorization: Bearer mem_live_..." \
  -H "Content-Type: application/json" \
  -d '{"text": "User prefers Python for data analysis"}'

{
  "success": true,
  "data": {
    "id": "mem_xyz789",
    "text": "User prefers Python for data analysis",
    "created_at": "2024-01-15T10:30:00Z",
    "updated_at": "2024-01-15T10:30:00Z"
  }
}

Later, query naturally:

curl -X POST https://memoryapi.tensorheart.com/v1/query \
  -H "Authorization: Bearer mem_live_..." \
  -H "Content-Type: application/json" \
  -d '{"context": "What programming language should I suggest?"}'

{
  "success": true,
  "data": {
    "memories": [
      {
        "id": "mem_xyz789",
        "text": "User prefers Python for data analysis",
        "relevance_score": 0.94
      }
    ],
    "query_context": "What programming language should I suggest?",
    "total_memories_searched": 3
  }
}

That's it. Your AI now has memory.

Next Steps

Ready to add memory to your AI?

• Quickstart — Get running in 5 minutes
• Building Agents — Add memory to your agent
• Use Cases — See real-world examples