Memory Search (SOTA)
技能 已验证 活跃SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting
To enable advanced, multi-strategy semantic search and knowledge retrieval from agent memory, improving the accuracy and relevance of information accessed.
功能
- Hybrid sparse+dense semantic search
- Graph RAG for multi-hop knowledge retrieval
- MMR diversity reranking for varied results
- Recency weighting to boost recent entries
- Support for multiple namespaces and strategy selection
使用场景
- Finding relevant information for complex reasoning tasks.
- Retrieving diverse results for broad queries.
- Prioritizing recent information in search results.
- Searching across different memory namespaces.
非目标
- Performing actions or modifying memory content.
- Providing a general-purpose natural language interface.
- Executing arbitrary code or external scripts.
工作流
- Parse query and flags
- Select retrieval strategy (dense, hybrid, graph-rag, smart)
- Apply MMR reranking
- Apply recency weighting
- Synthesize context (for complex queries)
- Present results
安装
请先添加 Marketplace
/plugin marketplace add ruvnet/ruflo/plugin install ruflo-rag-memory@ruflo质量评分
已验证类似扩展
Rag Architect
100Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Wrap Up Ritual
100End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
TradeMemory Protocol
100Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。
Cortex Debug Memory
100Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality', 'rate this memory', 'restore checkpoint', 'undo', or when memories are returning incorrect or stale results.
Embeddings
99Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.