mcpField
M
memory-management

memory-management

github.com/ruvnetAgent workflows80.1k1.2k installsUpdated today
Repository

About memory-management

A memory-management skill for agents using AgentDB, with persistent storage and HNSW vector search. It supports semantic retrieval and reuse of patterns from previous tasks.

Key features

  1. 01Store and retrieve memory entries
  2. 02Search by semantic similarity
  3. 03Organize entries by namespace
  4. 04Initialize HNSW vector indexing
  5. 05Export memory and view statistics

Use cases

  1. 01Save successful task patterns
  2. 02Find similar solutions from prior work
  3. 03Share stored knowledge among agents

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill memory-management

After installing, type/memory-managementin Claude Code to confirm it loaded.

Bundled filesscripts/memory-backup.shscripts/memory-consolidate.sh

Details

From the project README

Memory 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

ScriptPathDescription
memory-backup.agents/scripts/memory-backup.shBackup memory to external storage
memory-consolidate.agents/scripts/memory-consolidate.shConsolidate and optimize memory

References

DocumentPathDescription
HNSW Guidedocs/hnsw.mdHNSW vector search configuration
Memory Schemadocs/memory-schema.mdMemory namespace and schema reference

Best Practices

  1. Check memory for existing patterns before starting
  2. Use hierarchical topology for coordination
  3. Store successful patterns after completion
  4. Document any new learnings

Comments

Markdown supported