π 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: neural description: Neural pattern training, prediction, compression, and pipeline optimization
Neural system commands β dispatch by subcommand parsed from the user's input:
- train β
mcp__plugin_ruflo-core_ruflo__neural_trainwith{ modelType: "moe"|"transformer"|"classifier"|"embedding", epochs: N }(modelTypeis required). The CLI equivalent isneural train --pattern coordination|optimization|prediction|security|testing --epochs N. - status β
mcp__plugin_ruflo-core_ruflo__neural_status(SONA + MoE state, active patterns, training in flight). - patterns β
mcp__plugin_ruflo-core_ruflo__neural_patternswith{ action: "list"|"get"|"store"|"search"|"delete" }(default list;searchtakesqueryandlimit). - predict β
mcp__plugin_ruflo-core_ruflo__neural_predictwith{ input: "<task description>", topK? }to get a predicted outcome. - optimize β
mcp__plugin_ruflo-core_ruflo__neural_optimizeto retune the pipeline based on recent outcomes. - compress β
mcp__plugin_ruflo-core_ruflo__neural_compressto compact stored patterns (storage efficiency, runs after consolidation).
Present results clearly. For train, surface the loss curve summary; for predict, show the predicted agent + confidence; for optimize/compress, show before/after counts.