Memory Management
FreeEnhance learning and knowledge sharing with persistent memory.
Free · Opens the source repo
What Memory Management does
The Memory Management skill provides an advanced memory system for agents, utilizing HNSW vector search to offer rapid pattern retrieval and semantic search capabilities. With performance improvements ranging from 150x to 12,500x faster than traditional methods, this skill is designed for developers and designers who need to store, retrieve, and manage knowledge effectively. It allows users to create a persistent storage solution that can significantly enhance learning from past experiences and streamline knowledge sharing between agents.
This skill is particularly useful in scenarios where successful patterns or solutions need to be documented and accessed later. By enabling semantic lookups, users can easily find relevant information based on context rather than exact matches, making it ideal for tasks that require learning from previous work or sharing insights across multiple agents. The ability to store, retrieve, and manage knowledge efficiently can lead to improved productivity and better decision-making.
The commands available within this skill allow users to store patterns, perform semantic searches, retrieve specific entries, list all memory items, and delete entries as needed. Additionally, users can back up their memory, optimize it, and even export it for external use. This comprehensive set of features ensures that users can maintain an organized and efficient knowledge management system tailored to their needs.
While the Memory Management skill is powerful, it is best suited for environments where ongoing learning and knowledge retention are essential. If your tasks are one-off or do not require a learning component, this skill may not be necessary. However, for those looking to build a knowledge base or enhance their agents' capabilities through shared learning, this skill is an invaluable addition.
When to use it
Use this skill when you need to store successful patterns, conduct semantic searches, or manage knowledge over time.
When not to use it
Skip this skill for ephemeral tasks or when external data sources suffice for your needs.
What you can build with it
Storing Successful Patterns
Use the skill to document successful coding patterns or solutions for future reference.
Semantic Lookup for Best Practices
Conduct semantic searches to find relevant best practices from past projects quickly.
Knowledge Sharing Between Agents
Facilitate knowledge sharing by storing and retrieving insights that can be accessed by multiple agents.
How to install Memory Management
View source1. Install with the skills CLI
npx skills add ruvnet/ruflo/memory-management --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by ruvnetMemory Management Skill
Purpose
AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management.
When to Trigger
- need to store successful patterns
- searching for similar solutions
- semantic lookup of past work
- learning from previous tasks
- sharing knowledge between agents
- building knowledge base
When to Skip
- no learning needed
- ephemeral one-off tasks
- external data sources available
- read-only exploration
Commands
Store Pattern
Store a pattern or knowledge item in memory
npx @claude-flow/cli memory store --key "[key]" --value "[value]" --namespace patterns
Example:
npx @claude-flow/cli memory store --key "auth-jwt-pattern" --value "JWT validation with refresh tokens" --namespace patterns
Semantic Search
Search memory using semantic similarity
npx @claude-flow/cli memory search --query "[search terms]" --limit 10
Example:
npx @claude-flow/cli memory search --query "authentication best practices" --limit 5
Retrieve Entry
Retrieve a specific memory entry by key
npx @claude-flow/cli memory get --key "[key]" --namespace [namespace]
Example:
npx @claude-flow/cli memory get --key "auth-jwt-pattern" --namespace patterns
List Entries
List all entries in a namespace
npx @claude-flow/cli memory list --namespace [namespace]
Example:
npx @claude-flow/cli memory list --namespace patterns --limit 20
Delete Entry
Delete a memory entry
npx @claude-flow/cli memory delete --key "[key]" --namespace [namespace]
Initialize HNSW Index
Initialize HNSW vector search index
npx @claude-flow/cli memory init --enable-hnsw
Memory Stats
Show memory usage statistics
npx @claude-flow/cli memory stats
Export Memory
Export memory to JSON
npx @claude-flow/cli memory export --output memory-backup.json
Scripts
| Script | Path | Description |
|---|---|---|
memory-backup | .agents/scripts/memory-backup.sh | Backup memory to external storage |
memory-consolidate | .agents/scripts/memory-consolidate.sh | Consolidate and optimize memory |
References
| Document | Path | Description |
|---|---|---|
HNSW Guide | docs/hnsw.md | HNSW vector search configuration |
Memory Schema | docs/memory-schema.md | Memory namespace and schema reference |
Best Practices
- Check memory for existing patterns before starting
- Use hierarchical topology for coordination
- Store successful patterns after completion
- Document any new learnings
Frequently asked questions about Memory Management
Similar skills
Mini Context Graph
Build a persistent knowledge base with structured retrieval.
Pinecone RAG
Build RAG pipelines with Pinecone as your vector database.
Amazon Bedrock
Build generative AI applications on AWS Bedrock.
Supermemory
Enhance AI agents with persistent memory and context.
RAG Implementation
Build knowledge-grounded AI systems with RAG.
Clarity Gate
Ensure documents meet epistemic quality before ingestion.