Memoid

Introduction

What is Memoid and why you need it

Memoid is an open-source memory layer that gives your AI applications persistent, intelligent memory.

The Problem

AI applications are stateless by design. Every conversation starts fresh - your chatbot can’t remember a user’s name from five minutes ago, let alone their preferences from last week.

Developers typically work around this by:

  • Stuffing conversation history into prompts (hits token limits)
  • Manual database queries (misses semantic connections)
  • Building custom memory systems (expensive, error-prone)

The Solution

Memoid handles memory with a simple API:

from memoid import MemoryClient

client = MemoryClient("your-api-key")

# Add memory from a conversation
client.add(
    messages=[
        {"role": "user", "content": "I'm a vegetarian"},
        {"role": "assistant", "content": "I'll remember that!"}
    ],
    user_id="user_123"
)

# Search for relevant context
results = client.search(
    query="What food should I recommend?",
    user_id="user_123"
)
# Returns: "User is vegetarian"

Key Features

Automatic Fact Extraction

Send conversations to Memoid, and it extracts key facts automatically. No parsing required.

Semantic Search

Search using natural language. Ask “What does the user like?” instead of exact keyword matches.

Knowledge Graphs

Extract entities and relationships. Understand that “John works at Acme” connects John and Acme.

Multi-tenant

Isolate memories by user, agent, or organization. Share when needed.

Self-hostable

Run on your infrastructure for complete data control, or use our managed cloud.

Use Cases

  • Chatbots — Remember user preferences across conversations
  • Customer Support — Instant context about customer history
  • Personalization — Adapt experiences based on learned behavior
  • Research — Build knowledge bases from conversations

Next Steps