Install
Terminal · npx$
npx skills add https://github.com/sickn33/antigravity-awesome-skills --skill agent-memory-systemsWorks with Paperclip
How Agent Memory Systems fits into a Paperclip company.
Agent Memory Systems drops into any Paperclip agent that handles this kind of work. Assign it to a specialist inside a pre-configured PaperclipOrg company and the skill becomes available on every heartbeat — no prompt engineering, no tool wiring.
S
SaaS FactoryPaired
Pre-configured AI company — 18 agents, 18 skills, one-time purchase.
$27$59
Explore packSource file
SKILL.md1088 linesExpandCollapse
---name: agent-memory-systemsdescription: "Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them."risk: safesource: vibeship-spawner-skills (Apache 2.0)date_added: 2026-02-27--- # Agent Memory Systems Memory is the cornerstone of intelligent agents. Without it, every interactionstarts from zero. This skill covers the architecture of agent memory: short-term(context window), long-term (vector stores), and the cognitive architecturesthat organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored factsmean nothing if you can't find the right one. Chunking, embedding, and retrievalstrategies determine whether your agent remembers or forgets. The field is fragmented with inconsistent terminology. We use the CoALA cognitivearchitecture framework: semantic memory (facts), episodic memory (experiences),and procedural memory (how-to knowledge). ## Principles - Memory quality = retrieval quality, not storage quantity- Chunk for retrieval, not for storage- Context isolation is the enemy of memory- Right memory type for right information- Decay old memories - not everything should be forever- Test retrieval accuracy before production- Background memory formation beats real-time ## Capabilities - agent-memory- long-term-memory- short-term-memory- working-memory- episodic-memory- semantic-memory- procedural-memory- memory-retrieval- memory-formation- memory-decay ## Scope - vector-database-operations → data-engineer- rag-pipeline-architecture → llm-architect- embedding-model-selection → ml-engineer- knowledge-graph-design → knowledge-engineer ## Tooling ### Memory_frameworks - LangMem (LangChain) - When: LangGraph agents with persistent memory Note: Semantic, episodic, procedural memory types- MemGPT / Letta - When: Virtual context management, OS-style memory Note: Hierarchical memory tiers, automatic paging- Mem0 - When: User memory layer for personalization Note: Designed for user preferences and history ### Vector_stores - Pinecone - When: Managed, enterprise-scale (billions of vectors) Note: Best query performance, highest cost- Qdrant - When: Complex metadata filtering, open-source Note: Rust-based, excellent filtering- Weaviate - When: Hybrid search, knowledge graph features Note: GraphQL interface, good for relationships- ChromaDB - When: Prototyping, small/medium apps Note: Developer-friendly, ~20ms p50 at 100K vectors- pgvector - When: Already using PostgreSQL, simpler setup Note: Good for <1M vectors, familiar tooling ### Embedding_models - OpenAI text-embedding-3-large - When: Best quality, 3072 dimensions Note: $0.13/1M tokens- OpenAI text-embedding-3-small - When: Good balance, 1536 dimensions Note: $0.02/1M tokens, 5x cheaper- nomic-embed-text-v1.5 - When: Open-source, local deployment Note: 768 dimensions, good quality- all-MiniLM-L6-v2 - When: Lightweight, fast local embedding Note: 384 dimensions, lowest latency ## Patterns ### Memory Type Architecture Choosing the right memory type for different information **When to use**: Designing agent memory system # MEMORY TYPE ARCHITECTURE (CoALA Framework): """Three memory types for different purposes: 1. Semantic Memory: Facts and knowledge - What you know about the world - User preferences, domain knowledge - Stored in profiles (structured) or collections (unstructured) 2. Episodic Memory: Experiences and events - What happened (timestamped events) - Past conversations, task outcomes - Used for learning from experience 3. Procedural Memory: How to do things - Rules, skills, workflows - Often implemented as few-shot examples - "How did I solve this before?"""" ## LangMem Implementation"""from langmem import MemoryStorefrom langgraph.graph import StateGraph # Initialize memory storememory = MemoryStore( connection_string=os.environ["POSTGRES_URL"]) # Semantic memory: user profileawait memory.semantic.upsert( namespace="user_profile", key=user_id, content={ "name": "Alice", "preferences": ["dark mode", "concise responses"], "expertise_level": "developer", }) # Episodic memory: past interactionawait memory.episodic.add( namespace="conversations", content={ "timestamp": datetime.now(), "summary": "Helped debug authentication issue", "outcome": "resolved", "key_insights": ["Token expiry was root cause"], }, metadata={"user_id": user_id, "topic": "debugging"}) # Procedural memory: learned patternawait memory.procedural.add( namespace="skills", content={ "task_type": "debug_auth", "steps": ["Check token expiry", "Verify refresh flow"], "example_interaction": few_shot_example, })""" ## Memory Retrieval at Runtime"""async def prepare_context(user_id, query): # Get user profile (semantic) profile = await memory.semantic.get( namespace="user_profile", key=user_id ) # Find relevant past experiences (episodic) similar_experiences = await memory.episodic.search( namespace="conversations", query=query, filter={"user_id": user_id}, limit=3 ) # Find relevant skills (procedural) relevant_skills = await memory.procedural.search( namespace="skills", query=query, limit=2 ) return { "profile": profile, "past_experiences": similar_experiences, "relevant_skills": relevant_skills, }""" ### Vector Store Selection Pattern Choosing the right vector database for your use case **When to use**: Setting up persistent memory storage # VECTOR STORE SELECTION: """Decision matrix: | | Pinecone | Qdrant | Weaviate | ChromaDB | pgvector ||------------|----------|--------|----------|----------|----------|| Scale | Billions | 100M+ | 100M+ | 1M | 1M || Managed | Yes | Both | Both | Self | Self || Filtering | Basic | Best | Good | Basic | SQL || Hybrid | No | Yes | Best | No | Yes || Cost | High | Medium | Medium | Free | Free || Latency | 5ms | 7ms | 10ms | 20ms | 15ms |""" ## Pinecone (Enterprise Scale)"""from pinecone import Pinecone pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])index = pc.Index("agent-memory") # Upsert with metadataindex.upsert( vectors=[ { "id": f"memory-{uuid4()}", "values": embedding, "metadata": { "user_id": user_id, "timestamp": datetime.now().isoformat(), "type": "episodic", "content": memory_text, } } ], namespace=namespace) # Query with filterresults = index.query( vector=query_embedding, filter={"user_id": user_id, "type": "episodic"}, top_k=5, include_metadata=True)""" ## Qdrant (Complex Filtering)"""from qdrant_client import QdrantClientfrom qdrant_client.models import PointStruct, Filter, FieldCondition client = QdrantClient(url="http://localhost:6333") # Complex filtering with Qdrantresults = client.search( collection_name="agent_memory", query_vector=query_embedding, query_filter=Filter( must=[ FieldCondition(key="user_id", match={"value": user_id}), FieldCondition(key="type", match={"value": "semantic"}), ], should=[ FieldCondition(key="topic", match={"any": ["auth", "security"]}), ] ), limit=5)""" ## ChromaDB (Prototyping)"""import chromadb client = chromadb.PersistentClient(path="./memory_db")collection = client.get_or_create_collection("agent_memory") # Simple and fast for prototypescollection.add( ids=[str(uuid4())], embeddings=[embedding], documents=[memory_text], metadatas=[{"user_id": user_id, "type": "episodic"}]) results = collection.query( query_embeddings=[query_embedding], n_results=5, where={"user_id": user_id})""" ### Chunking Strategy Pattern Breaking documents into retrievable chunks **When to use**: Processing documents for memory storage # CHUNKING STRATEGIES: """The chunking dilemma:- Too large: Vector loses specificity- Too small: Loses context Optimal chunk size depends on:- Document type (code vs prose vs data)- Query patterns (factual vs exploratory)- Embedding model (each has sweet spot) General guidance: 256-512 tokens for most use cases""" ## Fixed-Size Chunking (Baseline)"""from langchain.text_splitter import RecursiveCharacterTextSplitter splitter = RecursiveCharacterTextSplitter( chunk_size=500, # Characters chunk_overlap=50, # Overlap prevents cutting sentences separators=["\n\n", "\n", ". ", " ", ""] # Priority order) chunks = splitter.split_text(document)""" ## Semantic Chunking (Better Quality)"""from langchain_experimental.text_splitter import SemanticChunkerfrom langchain_openai import OpenAIEmbeddings # Splits based on semantic similaritysplitter = SemanticChunker( embeddings=OpenAIEmbeddings(), breakpoint_threshold_type="percentile", breakpoint_threshold_amount=95) chunks = splitter.split_text(document)""" ## Structure-Aware Chunking (Documents with Hierarchy)"""from langchain.text_splitter import MarkdownHeaderTextSplitter # Respect document structuresplitter = MarkdownHeaderTextSplitter( headers_to_split_on=[ ("#", "Header 1"), ("##", "Header 2"), ("###", "Header 3"), ]) chunks = splitter.split_text(markdown_doc)# Each chunk has header metadata for context""" ## Contextual Chunking (Anthropic's Approach)"""# Add context to each chunk before embedding# Reduces retrieval failures by 35% def add_context_to_chunk(chunk, document_summary): context_prompt = f''' Document summary: {document_summary} The following is a chunk from this document: {chunk} ''' return context_prompt # Embed the contextualized chunk, not raw chunkfor chunk in chunks: contextualized = add_context_to_chunk(chunk, summary) embedding = embed(contextualized) store(chunk, embedding) # Store original, embed contextualized""" ## Code-Specific Chunking"""from langchain.text_splitter import Language, RecursiveCharacterTextSplitter # Language-aware splittingpython_splitter = RecursiveCharacterTextSplitter.from_language( language=Language.PYTHON, chunk_size=1000, chunk_overlap=200) # Respects function/class boundarieschunks = python_splitter.split_text(python_code)""" ### Background Memory Formation Processing memories asynchronously for better quality **When to use**: You want higher recall without slowing interactions # BACKGROUND MEMORY FORMATION: """Real-time memory extraction slows conversations and addscomplexity to agent tool calls. Background processing afterconversations yields higher quality memories. Pattern: Subconscious memory formation""" ## LangGraph Background Processing"""from langgraph.graph import StateGraphfrom langgraph.checkpoint.postgres import PostgresSaver async def background_memory_processor(thread_id: str): # Run after conversation ends or goes idle conversation = await load_conversation(thread_id) # Extract insights without time pressure insights = await llm.invoke(''' Analyze this conversation and extract: 1. Key facts learned about the user 2. User preferences revealed 3. Tasks completed or pending 4. Patterns in user behavior Be thorough - this runs in background. Conversation: {conversation} ''') # Store to long-term memory for insight in insights: await memory.semantic.upsert( namespace="user_insights", key=generate_key(insight), content=insight, metadata={"source_thread": thread_id} ) # Trigger on conversation end or idle timeout@on_conversation_idle(timeout_minutes=5)async def process_conversation(thread_id): await background_memory_processor(thread_id)""" ## Memory Consolidation (Like Sleep)"""# Periodically consolidate and deduplicate memories async def consolidate_memories(user_id: str): # Get all memories for user memories = await memory.semantic.list( namespace="user_insights", filter={"user_id": user_id} ) # Find similar memories (potential duplicates) clusters = cluster_by_similarity(memories, threshold=0.9) # Merge similar memories for cluster in clusters: if len(cluster) > 1: merged = await llm.invoke(f''' Consolidate these related memories into one: {cluster} Preserve all important information. ''') await memory.semantic.upsert( namespace="user_insights", key=generate_key(merged), content=merged ) # Delete originals for old in cluster: await memory.semantic.delete(old.id)""" ### Memory Decay Pattern Forgetting old, irrelevant memories **When to use**: Memory grows large, retrieval slows down # MEMORY DECAY: """Not all memories should live forever:- Old preferences may be outdated- Task details lose relevance- Conflicting memories confuse retrieval Implement intelligent decay based on:- Recency (when was it created/accessed?)- Frequency (how often is it retrieved?)- Importance (is it a core fact or detail?)""" ## Time-Based Decay"""from datetime import datetime, timedelta async def decay_old_memories(namespace: str, max_age_days: int): cutoff = datetime.now() - timedelta(days=max_age_days) old_memories = await memory.episodic.list( namespace=namespace, filter={"last_accessed": {"$lt": cutoff.isoformat()}} ) for mem in old_memories: # Soft delete (mark as archived) await memory.episodic.update( id=mem.id, metadata={"archived": True, "archived_at": datetime.now()} )""" ## Utility-Based Decay (MIRIX Approach)"""def calculate_memory_utility(memory): ''' Composite utility score inspired by cognitive science: - Recency: When was it last accessed? - Frequency: How often is it accessed? - Importance: How critical is this information? ''' now = datetime.now() # Recency score (exponential decay with 72h half-life) hours_since_access = (now - memory.last_accessed).total_seconds() / 3600 recency_score = 0.5 ** (hours_since_access / 72) # Frequency score frequency_score = min(memory.access_count / 10, 1.0) # Importance (from metadata or heuristic) importance = memory.metadata.get("importance", 0.5) # Weighted combination utility = ( 0.4 * recency_score + 0.3 * frequency_score + 0.3 * importance ) return utility async def prune_low_utility_memories(threshold=0.2): all_memories = await memory.list_all() for mem in all_memories: if calculate_memory_utility(mem) < threshold: await memory.archive(mem.id)""" ## Sharp Edges ### Chunking Isolates Information From Its Context Severity: CRITICAL Situation: Processing documents for vector storage Symptoms:Retrieval finds chunks but they don't make sense alone. Agentanswers miss the big picture. "The function returns X" retrievedwithout knowing which function. References to "this" withoutknowing what "this" refers to. Why this breaks:When we chunk for AI processing, we're breaking connections,reducing a holistic narrative to isolated fragments that oftenmiss the big picture. A chunk about "the configuration" withoutcontext about what system is being configured is nearly useless. Recommended fix: ## Contextual Chunking (Anthropic's approach)# Add document context to each chunk before embedding# Reduces retrieval failures by 35% def contextualize_chunk(chunk, document): summary = summarize(document) # LLM generates context for chunk context = llm.invoke(f''' Document summary: {summary} Generate a brief context statement for this chunk that would help someone understand what it refers to: {chunk} ''') return f"{context}\n\n{chunk}" # Embed t