Skip to main content

Tensorheart Memory

Give your AI applications memory. Store, retrieve, and use context intelligently.

The Problem​

LLMs forget everything after each request. Memory solves this by:

  • Storing important information as it's learned
  • Retrieving only what's relevant to each query
  • Reducing costs by sending less context

Quick Example​

Store a memory:

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_abc123",
    "text": "User prefers Python for data analysis",
    "created_at": "2024-01-15T10:30:00Z",
    "updated_at": "2024-01-15T10:30:00Z"
  }
}

Query for relevant memories:

curl -X POST https://memoryapi.tensorheart.com/v1/query \
  -H "Authorization: Bearer mem_live_..." \
  -H "Content-Type: application/json" \
  -d '{"context": "What language should I suggest for their project?"}'
{
  "success": true,
  "data": {
    "memories": [
      {
        "id": "mem_abc123",
        "text": "User prefers Python for data analysis",
        "relevance_score": 0.92
      }
    ],
    "query_context": "What language should I suggest for their project?",
    "total_memories_searched": 15
  }
}

Get Started​

5-Min Quickstart

Get your API key and make your first request.

Start Here

Why Memory?

Understand how memory works and why it matters.

Learn More

Build a Chatbot

Step-by-step tutorial to build a chatbot with memory.

Try Tutorial

Use Cases​

ApplicationWhat Memory Enables
Customer SupportRemember user history, past issues, preferences
Personal AssistantLearn habits, preferences, important dates
Code AssistantUnderstand codebase, remember patterns
Sales AIPersonalize with CRM data and conversation history

Building Agents?​

Check out the Building Agents with Memory guide for patterns that work with any framework.

Key Features​

FeatureDescription
Intelligent RetrievalOnly returns memories relevant to your query
Multi-tenantIsolated memory spaces per user or project
Auto-extractionAutomatically learn from conversations
Any LLMWorks with OpenAI, Anthropic, or any provider

Need Help?​