Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Memory Search (SOTA)

Skill Verifiziert Aktiv

SOTA semantic search — hybrid (sparse+dense), Graph RAG multi-hop, MMR diversity reranking, recency weighting

Zweck

To enable advanced, multi-strategy semantic search and knowledge retrieval from agent memory, improving the accuracy and relevance of information accessed.

Funktionen

  • 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

Anwendungsfälle

  • Finding relevant information for complex reasoning tasks.
  • Retrieving diverse results for broad queries.
  • Prioritizing recent information in search results.
  • Searching across different memory namespaces.

Nicht-Ziele

  • Performing actions or modifying memory content.
  • Providing a general-purpose natural language interface.
  • Executing arbitrary code or external scripts.

Workflow

  1. Parse query and flags
  2. Select retrieval strategy (dense, hybrid, graph-rag, smart)
  3. Apply MMR reranking
  4. Apply recency weighting
  5. Synthesize context (for complex queries)
  6. Present results

Installation

Zuerst Marketplace hinzufügen

/plugin marketplace add ruvnet/ruflo
/plugin install ruflo-rag-memory@ruflo

Qualitätspunktzahl

Verifiziert
97 /100
Analysiert about 21 hours ago

Vertrauenssignale

Letzter Commitabout 23 hours ago
Sterne50.2k
LizenzMIT
Status
Quellcode ansehen

Ähnliche Erweiterungen

Rag Architect

100

Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.

Skill
alirezarezvani

Chat Format

100

Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

Skill
ruvnet

Wrap Up Ritual

100

End-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.

Skill
rohitg00

TradeMemory Protocol

100

Domänenwissen für die Evolution Engine — LLM-gestützte autonome Strategieentdeckung aus rohen OHLCV-Daten. Behandelt die Schleife Generieren-Backtesten-Auswählen-Entwickeln, vektorisiertes Backtesting, Out-of-Sample-Validierung und Strategiegraduierung. Verwenden Sie es beim Entdecken von Handelspatterns, Ausführen von Backtests, Entwickeln von Strategien oder Überprüfen von Evolutionsprotokollen. Löst aus bei "evolve", "discover patterns", "backtest", "evolution", "strategy generation", "candidate strategy".

Skill
mnemox-ai

Cortex Debug Memory

100

Debug 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.

Skill
cdeust

Embeddings

99

Vector 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.

Skill
ruvnet