Skip to main content

​
Remember everything.

Memory Machines is building Large Memory Models (LMMs) to augment human cognition. Our mission is to endow humans with infinite memory — every person you ever met, every conversation ever had, every place ever visited, all accessible with searchless, promptless recall. The Memory Machines API is your gateway to this future. Upload your documents, and our LMMs transform them into structured episodic memories that can be queried naturally.

​
What are Large Memory Models?

LMMs are a new class of AI models beyond LLMs. Built on decades of neuroscience research, they mimic human associative memory — how the brain stores, links, and retrieves experiences. Instead of just processing text, LMMs understand memory.

​
How It Works

1

Memorize

Send documents to the /v1/memorize endpoint. Emails, meeting notes, journal entries — any text content that captures your experiences.
2

LMM Extracts Memories

Our Large Memory Models extract structured episodic memories from your content, identifying narratives, participants, time, place, and semantic connections.
3

Ask or Recall

Ask questions in natural language via /v1/memories/ask, or retrieve raw memories with /v1/memories/recall.

​
Quick Example

# Memorize a document
curl -X POST https://memorymachines-core-api-mvp-gateway-6v1lw71z.uc.gateway.dev/v1/memorize \
  -H "x-api-key: YOUR_API_KEY" \
  -F "file=@meeting-notes.txt" \
  -F "user_name=john_doe" \
  -F "source_type=meeting"

# Ask your memories
curl -X POST https://memorymachines-core-api-mvp-gateway-6v1lw71z.uc.gateway.dev/v1/memories/ask \
  -H "x-api-key: YOUR_API_KEY" \
  -F "text=What did we decide about the product launch?"

​
Next Steps

Quick Start

Get up and running in 5 minutes

API Reference

Explore the full API