How Graph Memory Works - supermemory | Memory API for the AI era

Supermemory builds a living knowledge graph where memories connect to other memories. Unlike traditional knowledge graphs with entity-relation-entity triples, Supermemory’s graph is facts built on top of other facts.

Memory Relationships

When you add content, Supermemory extracts facts and automatically connects them to existing memories through three relationship types:

Updates: Information Changes

When new information contradicts existing knowledge:

Memory 1: "Alex works at Google as a software engineer"
Memory 2: "Alex just started at Stripe as a PM"
         ↓
Memory 2 UPDATES Memory 1

The system tracks which memory is latest with isLatest, so searches return current information while preserving history.

Extends: Information Enriches

When new information adds detail without replacing:

Memory 1: "Alex works at Stripe as a PM"
Memory 2: "Alex focuses on payments infrastructure and leads a team of 5"
         ↓
Memory 2 EXTENDS Memory 1

Both memories remain valid—searches get richer context.

Derives: Information Infers

When Supermemory infers new facts from patterns:

Memory 1: "Alex is a PM at Stripe"
Memory 2: "Alex frequently discusses payment APIs and fraud detection"
         ↓
Derived: "Alex likely works on Stripe's core payments product"

These inferences surface insights you didn’t explicitly state.

Automatic Memory Extraction

From a single conversation, Supermemory extracts multiple connected memories: Input:

“Had a great call with Alex. He’s enjoying the new PM role at Stripe, though the payments infrastructure work is intense. He moved to Seattle for the job—got a place in Capitol Hill. Wants to grab dinner next time I’m in town.”

Extracted memories:

Alex works at Stripe as a PM
Alex works on payments infrastructure (extends role memory)
Alex lives in Seattle, Capitol Hill (new fact)
Alex wants to meet for dinner (episodic)

Each fact is connected to related memories automatically.

Automatic Forgetting

Supermemory knows when memories become irrelevant: Time-based forgetting: Temporary facts are automatically forgotten when they expire.

"I have an exam tomorrow"
         ↓
    After the exam date passes → automatically forgotten

"Meeting with Alex at 3pm today"
         ↓
    After today → automatically forgotten

Contradiction resolution: When new facts contradict old ones, the Update relationship ensures searches return current information. Noise filtering: Casual, non-meaningful content doesn’t become permanent memories.

Memory Types

Supermemory distinguishes memory types automatically:

Type	Example	Behavior
Facts	”Alex is a PM at Stripe”	Persists until updated
Preferences	”Alex prefers morning meetings”	Strengthens with repetition
Episodes	”Met Alex for coffee Tuesday”	Decays unless significant

What You Don’t Do

All of this is automatic. You don’t:

Define relationships manually
Tag memory types
Clean up old memories
Resolve contradictions

Just add content and search naturally:

await client.add({
  content: "Alex mentioned he just started at Stripe"
});

const results = await client.search({
  query: "where does Alex work?"
});
// → Stripe (latest), previously Google (historical)

Learn More

How It Works

Deep dive into the architecture

Memory vs RAG

When to use memory vs document retrieval

User Profiles

Automatic summaries from the graph

Add Memories

Start building your knowledge graph

​Memory Relationships

​Updates: Information Changes

​Extends: Information Enriches

​Derives: Information Infers

​Automatic Memory Extraction

​Automatic Forgetting

​Memory Types

​What You Don’t Do

​Learn More