skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
eyadsibai/ltk65 installs

memory-systems

Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"

How do I install this agent skill?

npx skills add https://github.com/eyadsibai/ltk --skill memory-systems
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill provides architectural guidance and code patterns for implementing agent memory systems. It is safe to use but involves handling user data, which introduces inherent risks of indirect prompt injection if stored content is not properly sanitized before retrieval.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

  • Runlayerpass

    1 file scanned · No issues

What does this agent skill do?

Memory System Design

Memory provides persistence that allows agents to maintain continuity across sessions and reason over accumulated knowledge.

Memory Architecture Spectrum

LayerLatencyPersistenceUse Case
Working MemoryZeroVolatileContext window
Short-TermLowSessionSession state
Long-TermMediumPersistentCross-session knowledge
Entity MemoryMediumPersistentEntity tracking
Temporal KGMediumPersistentTime-aware queries

Memory System Performance

SystemDMR AccuracyRetrieval Latency
Zep (Temporal KG)94.8%2.58s
MemGPT93.4%Variable
GraphRAG75-85%Variable
Vector RAG60-70%Fast
Recursive Summary35.3%Low

Why Vector Stores Fall Short

Vector stores lose relationship information:

  • Can retrieve "Customer X purchased Product Y"
  • Cannot answer "What did customers who bought Y also buy?"
  • Cannot distinguish current vs outdated facts

Memory Implementation Patterns

Pattern 1: File-System-as-Memory

# Simple, no infrastructure needed
def store_fact(entity_id, fact):
    path = f"memory/{entity_id}.json"
    facts = load_json(path, default=[])
    facts.append({"fact": fact, "timestamp": now()})
    save_json(path, facts)

Pattern 2: Vector RAG with Metadata

# Embed facts with rich metadata
vector_store.add(
    embedding=embed(fact),
    metadata={
        "entity_id": entity_id,
        "valid_from": now(),
        "source": "conversation",
        "confidence": 0.95
    }
)

Pattern 3: Knowledge Graph

# Preserve relationships
graph.create_relationship(
    from_entity="Customer_123",
    relationship="PURCHASED",
    to_entity="Product_456",
    properties={"date": "2024-01-15", "quantity": 2}
)

Pattern 4: Temporal Knowledge Graph

# Time-travel queries
def query_address_at_time(user_id, query_time):
    return graph.query("""
        MATCH (user)-[r:LIVES_AT]->(address)
        WHERE user.id = $user_id
        AND r.valid_from <= $query_time
        AND (r.valid_until IS NULL OR r.valid_until > $query_time)
        RETURN address
    """, {"user_id": user_id, "query_time": query_time})

Entity Memory

Track entities consistently across conversations:

  • Entity Identity: "John Doe" in one conversation = same person in another
  • Entity Properties: Facts discovered about entities over time
  • Entity Relationships: Relationships discovered between entities
def remember_entity(entity_id, properties):
    memory.store({
        "type": "entity",
        "id": entity_id,
        "properties": properties,
        "last_updated": now()
    })

Memory Consolidation

Trigger consolidation when:

  • Memory accumulates significantly
  • Retrieval returns too many outdated results
  • Periodically on schedule
  • Explicit request

Process:

  1. Identify outdated facts
  2. Merge related facts
  3. Update validity periods
  4. Archive/delete obsolete facts
  5. Rebuild indexes

Choosing Memory Architecture

RequirementArchitecture
Simple persistenceFile-system memory
Semantic searchVector RAG with metadata
Relationship reasoningKnowledge graph
Temporal validityTemporal knowledge graph

Best Practices

  1. Match architecture to query requirements
  2. Implement progressive disclosure for access
  3. Use temporal validity to prevent conflicts
  4. Consolidate periodically
  5. Design for retrieval failures gracefully
  6. Consider privacy implications
  7. Implement backup and recovery
  8. Monitor growth and performance

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/eyadsibai/ltk/memory-systems">View memory-systems on skillZs</a>