Memory Management

​

Overview

​

Memory Lifecycle

Input → Embedding → Deduplication → Store → Retrieve → Consolidate

1. Input — Raw content arrives
2. Embedding — Vector generated for semantic search
3. Deduplication — Checked against existing memories
4. Store — Persisted with metadata
5. Retrieve — Loaded during tick context building
6. Consolidate — Periodically merged into core memories

​

Deduplication Tuning

​

Custom Thresholds

import { checkDuplication, DEDUP_THRESHOLDS } from "./src/memory/deduplication";

const result = checkDuplication(newMemory, existingMemories, {
  typeThresholds: {
    ...DEDUP_THRESHOLDS,
    semantic: 0.90  // More aggressive semantic dedup
  }
});

​

Finding Similar Memories

import { findSimilarMemories } from "./src/memory/deduplication";

const similar = findSimilarMemories(targetMemory, allMemories, {
  limit: 5,
  minSimilarity: 0.6
});

​

Salience and Confidence

• Boosted by: exclamation marks, caps, urgency words
• Lowered by: routine phrasing, generic content

• Boosted by: API sources, verified data
• Lowered by: user input, opinions

import { calculateSalience, calculateConfidence } from "./src/memory/deduplication";

const salience = calculateSalience("Breaking: Major announcement!");  // ~0.8
const confidence = calculateConfidence("Price is $100", "api");       // ~0.9

​

Embedding Providers

​

Retrieval Patterns

​

Filter by Type

const semanticMemories = await agent.memory.get({ type: "semantic", limit: 20 });
const reflections = await agent.memory.get({ type: "reflection", limit: 10 });

​

Semantic Search

const results = await agent.memory.search({ query: "market trends", limit: 10 });

​

Get Statistics

const stats = await agent.memory.getStats();
// { total, byType, byScope, averageImportance }

​

Memory Consolidation (Roadmap)

1. Cluster similar memories by embedding
2. Extract common themes
3. Generate summary content
4. Link core memory to sources

​

Memory Linking (Roadmap)

• caused_by — Causal relationship
• related_to — General association
• contradicts — Conflicting information
• elaborates — Adds detail
• supersedes — Replaces old info
• temporal_before / temporal_after — Time ordering

​

Best Practices

• Tune thresholds for your domain using real data
• Monitor storage growth and implement pruning if needed
• Use metadata effectively—tags, sources, context
• Cache embeddings to reduce API costs
• Batch operations when storing many memories

​

Next Steps