V3 Memory Unification
技能 已验证 活跃Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
To streamline and accelerate AI agent memory management by unifying disparate systems into a high-performance, searchable AgentDB.
功能
- Unify 6+ memory systems
- Implement HNSW indexing for search
- Achieve 150x-12,500x search speed improvements
- Migrate data from SQLite and Markdown
- Integrate with SONA learning patterns
使用场景
- When needing to accelerate agent memory retrieval
- When managing multiple, incompatible memory backends
- When migrating historical agent data to a unified system
- When integrating learning patterns into agent memory
非目标
- Replacing the LLM provider
- Providing a general-purpose database
- Managing agent task execution directly (focus is memory)
工作流
- Design AgentDB unification strategy
- Configure HNSW indexing and vector search
- Migrate data from SQLite/Markdown to AgentDB
- Store and query memory entries via unified interface
- Integrate learning patterns into memory
实践
- Memory management
- Data migration
- Performance optimization
- System integration
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
已验证类似扩展
Memory Management
99AgentDB 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.
V3 Memory Specialist
99Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
Mongodb Search And Ai
100指导 MongoDB 用户实现和优化 Atlas Search（全文搜索）、Vector Search（语义搜索）和 Hybrid Search 解决方案。当用户需要为文本查询（自动完成、模糊匹配、分面搜索）、语义相似性（嵌入、RAG 应用）或组合方法构建搜索功能时，请使用此技能。当用户需要文本包含、子字符串匹配（“包含”、“包括”、“出现在”）、不区分大小写或多字段文本搜索，或跨多个字段进行具有可变组合的过滤时，也请使用此技能。提供有关选择正确的搜索类型、创建索引、构建查询和使用 MongoDB MCP 服务器优化性能的工作流。
Dsql
100Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL migration, DDL operations, query plan explainability, and SQL compatibility validation. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow.
Agentdb Query
99Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
Migrate Create
99Create a new sequentially numbered database migration with up/down SQL files