Skip to main content
Mem[v] provides graph-based memory infrastructure for AI agents, automatically extracting entities, building knowledge graphs, and enabling semantic retrieval across all content types.

​
The workflow

1

Connect your content

Upload files or send data through the API:
  • Documents (PDFs, Word, text)
  • Videos (MP4, MOV, WebM)
  • Audio (MP3, WAV)
  • Images and screenshots
  • Conversations
2

Automatic extraction

Mem[v] processes content and extracts:
  • Entities (people, companies, technologies, topics)
  • Relationships between entities
  • Semantic embeddings for search
  • Temporal context and metadata
3

Graph construction

Information is organized into knowledge graphs:
  • Entities become nodes
  • Relationships become edges
  • Triplets form: Subject → Predicate → Object
  • Isolated within Spaces for privacy
4

Semantic retrieval

Query by meaning to retrieve relevant context:
  • Graph-aware search returns connected information
  • Results ranked by relevance
  • Include entity relationships and metadata

​
Key concepts

​
Spaces

Isolated containers for memories and knowledge graphs. Each space has complete data separation, enabling per-user, per-feature, or per-tenant organization.

​
Memories

Structured information extracted from your content. Each memory contains content, metadata, and extracted entities that feed into the knowledge graph.

​
Knowledge graphs

Automatically built networks connecting entities through relationships. Enable discovery of indirect connections and richer context for AI agents. Graph-aware retrieval that finds information by meaning and returns connected entities and relationships.

​
Data flow

Content → Processing → Memories → Knowledge Graph
                          ↓
AI Agent ← Semantic Search ← Query

​
Next steps

Quickstart

Build your first memory-enabled app

Spaces

Organize memories with Spaces

Knowledge Graphs

Understand graph-based memory

SDK Documentation

Explore the SDKs