跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Memory Management

技能 已验证 活跃

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. Use when: 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. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

目的

To offer a persistent and semantically searchable memory system for AI agents, enabling learning, knowledge management, and faster pattern retrieval through HNSW vector search.

功能

  • Persistent agent memory storage
  • HNSW vector search for faster retrieval
  • Semantic search capabilities
  • Commands for CRUD operations on memory entries
  • Memory statistics and export functionality

使用场景

  • Storing successful agent patterns
  • Searching for similar solutions in memory
  • Semantic lookup of past work
  • Learning from previous agent tasks
  • Building a knowledge base for agents

非目标

  • No learning needed
  • Ephemeral one-off tasks
  • External data sources
  • Read-only exploration

安装

npx skills add ruvnet/ruflo

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
99 /100
about 24 hours ago 分析

信任信号

最近提交1 day ago
星标50.2k
许可证MIT
状态
查看源代码