🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
name: embeddings description: RuVector embedding engine status and operations -- ONNX, HNSW, RaBitQ quantization
Embedding engine commands:
- Call
mcp__plugin_ruflo-core_ruflo__embeddings_statusto check the ONNX embedding engine. - Show: model (all-MiniLM-L6-v2), dimensions (384), HNSW index status, cache hit rate.
- If not initialized, suggest calling
mcp__plugin_ruflo-core_ruflo__embeddings_init. - For search, use
mcp__plugin_ruflo-core_ruflo__embeddings_searchwith the user's query (namespace-filtered). - For large-corpus search with memory pressure, use the RaBitQ quantized path (32× memory reduction):
- the index builds itself on first use and rebuilds when the corpus drifts >20%; call
mcp__plugin_ruflo-core_ruflo__embeddings_rabitq_buildto force one now mcp__plugin_ruflo-core_ruflo__embeddings_rabitq_search(Hamming-prefilter to top-N candidates)mcp__plugin_ruflo-core_ruflo__embeddings_rabitq_statusfor index health
- the index builds itself on first use and rebuilds when the corpus drifts >20%; call
- For hierarchical data (taxonomies, code trees), use
mcp__plugin_ruflo-core_ruflo__embeddings_hyperbolic(Poincare ball model). - The substrate-level entry point
mcp__plugin_ruflo-core_ruflo__embeddings_neuralexists; in normal use it's covered byembeddings_init+embeddings_generate.