Introduction

Memokit is a Memory as a Service platform that provides semantic memory storage and retrieval APIs for AI applications. Enable your AI agents with long-term memory capabilities, vector-based semantic search, entity extraction, and knowledge graphs.

What is Memokit?

Memokit allows AI applications to:

Store memories - Persist conversations, facts, and context with automatic vector embeddings
Search semantically - Find relevant memories using natural language queries
Extract entities - Automatically identify and track people, places, and concepts
Build relationships - Create knowledge graphs connecting entities

Key Features

Feature	Description
Semantic Search	Vector-based similarity search using state-of-the-art embeddings
Entity Extraction	Automatic identification of entities from memory content
Relationship Graphs	Connect entities with typed relationships
Webhooks	Real-time notifications for memory events
Multi-tenant	Isolated data per API key

Use Cases

AI Assistants

Give your AI assistants the ability to remember past conversations, user preferences, and learned facts.

Customer Support

Build support bots that remember customer history and context across sessions.

Knowledge Management

Create searchable knowledge bases with semantic understanding.

Research Tools

Build research assistants that can store and retrieve information contextually.

Quick Example

# Create a memory
curl -X POST https://api.memokit.dev/v1/memories \
  -H "Authorization: Bearer mk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "The user prefers dark mode and uses vim keybindings",
    "userId": "user_123"
  }'

# Search memories
curl -X POST https://api.memokit.dev/v1/memories/search \
  -H "Authorization: Bearer mk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "What are the user preferences?",
    "userId": "user_123"
  }'

Next Steps

Quickstart - Get up and running in 5 minutes
Authentication - Learn about API keys
API Reference - Explore the full API

Introduction

On this page