Implement agent memory - short-term, long-term, semantic storage, and retrieval
Enables persistent memory across conversations using buffers, summaries, or vector stores. Claude uses this when building agents that need to remember user preferences, maintain context over long sessions, or recall relevant past interactions for personalized responses.
/plugin marketplace add pluginagentmarketplace/custom-plugin-ai-agents/plugin install custom-plugin-ai-agents@pluginagentmarketplace-ai-agentsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/config.yamlassets/schema.jsonreferences/GUIDE.mdreferences/PATTERNS.mdscripts/multi_layer_memory.pyscripts/validate.pyGive agents the ability to remember and learn across conversations.
Invoke this skill when:
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
task | string | Yes | Memory goal | - |
memory_type | enum | No | buffer, summary, vector, hybrid | hybrid |
persistence | enum | No | session, user, global | session |
from langchain.memory import ConversationBufferWindowMemory
# Simple buffer (last k messages)
memory = ConversationBufferWindowMemory(k=10)
# With summarization
from langchain.memory import ConversationSummaryBufferMemory
memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=2000)
# Vector store memory
from langchain.memory import VectorStoreRetrieverMemory
memory = VectorStoreRetrieverMemory(retriever=vectorstore.as_retriever())
| Type | Use Case | Pros | Cons |
|---|---|---|---|
| Buffer | Short chats | Simple | No compression |
| Summary | Long chats | Compact | Loses detail |
| Vector | Semantic recall | Relevant | Slower |
| Hybrid | Production | Best of all | Complex |
class ProductionMemory:
def __init__(self):
self.short_term = BufferMemory(k=10) # Recent
self.summary = SummaryMemory() # Compressed
self.long_term = VectorMemory() # Semantic
| Issue | Solution |
|---|---|
| Context overflow | Add summarization |
| Slow retrieval | Cache, reduce k |
| Irrelevant recall | Improve embeddings |
| Memory not persisting | Check storage backend |
rag-systems - Vector retrievalllm-integration - Context managementai-agent-basics - Agent architectureThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.