Memory Management

by ruvnet60de638630abNo license74K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

AgentDB memory system with HNSW vector search. Use when: need to store patterns, search for solutions, semantic lookup. Skip when: no learning needed, ephemeral tasks.

Instructions onlyAI & Agents
AI-generated overview

Stores and semantically searches agent memory patterns using an AgentDB vector store via CLI commands.

What it does
This skill documents a memory system built on AgentDB with HNSW vector search. It provides command examples for storing a key-value pattern in a namespace and for running a semantic search over stored memory with a query and result limit. It also lists best practices such as checking memory before starting work and storing successful patterns afterward.
When to use it
Use it when an agent needs to persist reusable patterns or look up prior solutions semantically. It is intended for tasks where learning carries over between sessions, and it is meant to be skipped for ephemeral tasks or when no learning is needed.
Requirements
Requires the npx command and network access to fetch and run the @claude-flow/cli package. No scripts ship with the skill; it contains instructions and CLI command examples only.

Memory Management Skill

Purpose

AgentDB memory system with HNSW vector search.

When to Trigger

  • need to store patterns
  • search for solutions
  • semantic lookup

When to Skip

  • no learning needed
  • ephemeral tasks

Commands

Store Data

Store a pattern in memory

bash
npx @claude-flow/cli memory store --key "key" --value "value" --namespace patterns

Search Data

Semantic search in memory

bash
npx @claude-flow/cli memory search --query "search terms" --limit 10

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

Source and attribution

Source:ruvnet/rufloinv3/@claude-flow/codex/.agents/skills/memory-managementat commit60de638

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Memory Management Agent Skill | SourceWeft