Memory Search
Search Ruflo's stored memories. Select a strategy supported by the Ruflo CLI or MCP tool, and report which one actually ran.
Strategy selection
- Default: semantic retrieval through
memory searchor MCPmemory_search. --hybrid: CLI keyword + semantic result union, deduplicated and sorted by score. This is not theruvector searchCLI and does not claim Graph RAG or sparse/dense RRF.--smart: request query expansion, RRF across variants, recency weighting, and MMR diversity. The MCP tool can fall back to plain search if the installed memory package lackssmartSearch; inspect the returned fallback note before claiming SmartRetrieval ran.- Cross-namespace: MCP
memory_search_unifiedmerges and deduplicates results from multiple namespaces.
If the user requests --graph-rag, explain that this plugin has no supported text-query Graph RAG command. Offer --smart semantic retrieval as a clearly labeled fallback; do not claim graph traversal.
Steps
Parse the query, optional namespace, result limit, and strategy flags. Omit
--namespaceto search all namespaces. For CLI commands, treat the query as untrusted shell input: use POSIX single-quote escaping for embedded apostrophes and reject embedded newlines. Do not interpolate it inside double quotes.Run one of the supported paths:
Semantic (default)
npx @claude-flow/cli@latest memory search --query 'QUERY' --limit 10MCP:
mcp__plugin_ruflo-core_ruflo__memory_search({ query: "QUERY", limit: 10 })Keyword + semantic union (
--hybrid)npx @claude-flow/cli@latest memory search --query 'QUERY' --type hybrid --limit 10Add
--namespace NAMESPACEonly when the user requests one.Smart retrieval (
--smart)npx @claude-flow/cli@latest memory search --query 'QUERY' --smart --limit 10MCP:
mcp__plugin_ruflo-core_ruflo__memory_search({ query: "QUERY", smart: true, limit: 10 })Cross-namespace bridge search
mcp__plugin_ruflo-core_ruflo__memory_search_unified({ query: "QUERY", limit: 10 })Only when the question is about how earlier tasks like this one went, also ask for their validated episodes:
mcp__plugin_ruflo-core_ruflo__agentdb_context-synthesize({ query: "QUERY", maxEntries: 10 })It is not a document synthesizer: it summarizes validated task episodes (task, reward, success) and answersno-memoriesorno-eligible-episodesfor ordinary records, which is correct, not missing data.Present the returned entries with namespace attribution. Distinguish raw
similarityfrom SmartRetrieval'srankingScore; neither is a probability of truth. State when SmartRetrieval fell back to plain search.
Namespace guide
| Namespace | Typical content |
|---|---|
patterns |
Reusable approaches |
tasks |
Task context |
solutions |
Resolved problems |
feedback |
User corrections |
security |
Security notes |
| (omit) | All available namespaces |
