Agent memory
Skill pluginagentmarketplace/custom-plugin-ai-agents/skills/agent-memory
Implement agent memory - short-term, long-term, semantic storage, and retrievalFrom its SKILL.md
npx -y skills add pluginagentmarketplace/custom-plugin-ai-agents --skill agent-memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.5 KB, as published. Nobody here has run it
Agent Memory
Give agents the ability to remember and learn across conversations.
When to Use This Skill
Invoke this skill when:
- Adding conversation history
- Implementing long-term memory
- Building personalized agents
- Managing context windows
Parameter Schema
| 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 |
Quick Start
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())
Memory Types
| 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 |
Multi-Layer Architecture
class ProductionMemory:
def __init__(self):
self.short_term = BufferMemory(k=10) # Recent
self.summary = SummaryMemory() # Compressed
self.long_term = VectorMemory() # Semantic
Troubleshooting
| Issue | Solution |
|---|---|
| Context overflow | Add summarization |
| Slow retrieval | Cache, reduce k |
| Irrelevant recall | Improve embeddings |
| Memory not persisting | Check storage backend |
Best Practices
- Use multi-layer memory for production
- Set token limits to prevent overflow
- Add metadata (timestamps, importance)
- Implement TTL for old memories
Related Skills
rag-systems- Vector retrievalllm-integration- Context managementai-agent-basics- Agent architecture