Flow Nexus Neural

作者 ruvnet60de638630ab无许可证74K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库今天更新

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

仅含说明AI & AgentsDevOps & Cloud
AI 生成的概览

通过 Flow Nexus MCP 服务器在分布式 E2B 沙箱中训练、部署和管理神经网络。

功能
该技能说明如何使用 Flow Nexus MCP 工具训练神经网络，支持前馈、LSTM、GAN、自编码器和 Transformer 等架构，并可选择不同资源档位。内容涵盖运行推理、浏览和部署市场模板、初始化含工作节点、参数服务器和聚合节点的分布式训练集群、监控训练状态、性能基准测试、验证工作流，以及发布或评价模板。它是一份仅含说明的指南，提供配置示例，不附带脚本。
适用场景
当你需要通过 Flow Nexus 平台训练、部署或运维神经网络模型时使用，包括跨沙箱的分布式或联邦训练。它也适用于挑选预置市场模板、运行预测，或对已有模型进行基准测试与验证。
运行要求
需通过 npx flow-nexus@latest mcp start 添加 Flow Nexus MCP 服务器，并注册和登录以执行分布式训练等需认证的操作。需要访问 Flow Nexus 服务的网络连接；不附带任何脚本。

Flow Nexus Neural Networks

Deploy, train, and manage neural networks in distributed E2B sandbox environments. Train custom models with multiple architectures (feedforward, LSTM, GAN, transformer) or use pre-built templates from the marketplace.

Prerequisites

bash
# Add Flow Nexus MCP serverclaude mcp add flow-nexus npx flow-nexus@latest mcp start
# Register and loginnpx flow-nexus@latest registernpx flow-nexus@latest login

Core Capabilities

1. Single-Node Neural Training

Train neural networks with custom architectures and configurations.

Available Architectures:

  • feedforward - Standard fully-connected networks
  • lstm - Long Short-Term Memory for sequences
  • gan - Generative Adversarial Networks
  • autoencoder - Dimensionality reduction
  • transformer - Attention-based models

Training Tiers:

  • nano - Minimal resources (fast, limited)
  • mini - Small models
  • small - Standard models
  • medium - Complex models
  • large - Large-scale training
Example: Train Custom Classifier
javascript
mcp__flow-nexus__neural_train({  config: {    architecture: {      type: "feedforward",      layers: [        { type: "dense", units: 256, activation: "relu" },        { type: "dropout", rate: 0.3 },        { type: "dense", units: 128, activation: "relu" },        { type: "dropout", rate: 0.2 },        { type: "dense", units: 64, activation: "relu" },        { type: "dense", units: 10, activation: "softmax" }      ]    },    training: {      epochs: 100,      batch_size: 32,      learning_rate: 0.001,      optimizer: "adam"    },    divergent: {      enabled: true,      pattern: "lateral", // quantum, chaotic, associative, evolutionary      factor: 0.5    }  },  tier: "small",  user_id: "your_user_id"})
Example: LSTM for Time Series
javascript
mcp__flow-nexus__neural_train({  config: {    architecture: {      type: "lstm",      layers: [        { type: "lstm", units: 128, return_sequences: true },        { type: "dropout", rate: 0.2 },        { type: "lstm", units: 64 },        { type: "dense", units: 1, activation: "linear" }      ]    },    training: {      epochs: 150,      batch_size: 64,      learning_rate: 0.01,      optimizer: "adam"    }  },  tier: "medium"})
Example: Transformer Architecture
javascript
mcp__flow-nexus__neural_train({  config: {    architecture: {      type: "transformer",      layers: [        { type: "embedding", vocab_size: 10000, embedding_dim: 512 },        { type: "transformer_encoder", num_heads: 8, ff_dim: 2048 },        { type: "global_average_pooling" },        { type: "dense", units: 128, activation: "relu" },        { type: "dense", units: 2, activation: "softmax" }      ]    },    training: {      epochs: 50,      batch_size: 16,      learning_rate: 0.0001,      optimizer: "adam"    }  },  tier: "large"})

2. Model Inference

Run predictions on trained models.

javascript
mcp__flow-nexus__neural_predict({  model_id: "model_abc123",  input: [    [0.5, 0.3, 0.2, 0.1],    [0.8, 0.1, 0.05, 0.05],    [0.2, 0.6, 0.15, 0.05]  ],  user_id: "your_user_id"})

Response:

json
{  "predictions": [    [0.12, 0.85, 0.03],    [0.89, 0.08, 0.03],    [0.05, 0.92, 0.03]  ],  "inference_time_ms": 45,  "model_version": "1.0.0"}

3. Template Marketplace

Browse and deploy pre-trained models from the marketplace.

List Available Templates
javascript
mcp__flow-nexus__neural_list_templates({  category: "classification", // timeseries, regression, nlp, vision, anomaly, generative  tier: "free", // or "paid"  search: "sentiment",  limit: 20})

Response:

json
{  "templates": [    {      "id": "sentiment-analysis-v2",      "name": "Sentiment Analysis Classifier",      "description": "Pre-trained BERT model for sentiment analysis",      "category": "nlp",      "accuracy": 0.94,      "downloads": 1523,      "tier": "free"    },    {      "id": "image-classifier-resnet",      "name": "ResNet Image Classifier",      "description": "ResNet-50 for image classification",      "category": "vision",      "accuracy": 0.96,      "downloads": 2341,      "tier": "paid"    }  ]}
Deploy Template
javascript
mcp__flow-nexus__neural_deploy_template({  template_id: "sentiment-analysis-v2",  custom_config: {    training: {      epochs: 50,      learning_rate: 0.0001    }  },  user_id: "your_user_id"})

4. Distributed Training Clusters

Train large models across multiple E2B sandboxes with distributed computing.

Initialize Cluster
javascript
mcp__flow-nexus__neural_cluster_init({  name: "large-model-cluster",  architecture: "transformer", // transformer, cnn, rnn, gnn, hybrid  topology: "mesh", // mesh, ring, star, hierarchical  consensus: "proof-of-learning", // byzantine, raft, gossip  daaEnabled: true, // Decentralized Autonomous Agents  wasmOptimization: true})

Response:

json
{  "cluster_id": "cluster_xyz789",  "name": "large-model-cluster",  "status": "initializing",  "topology": "mesh",  "max_nodes": 100,  "created_at": "2025-10-19T10:30:00Z"}
Deploy Worker Nodes
javascript
// Deploy parameter servermcp__flow-nexus__neural_node_deploy({  cluster_id: "cluster_xyz789",  node_type: "parameter_server",  model: "large",  template: "nodejs",  capabilities: ["parameter_management", "gradient_aggregation"],  autonomy: 0.8})
// Deploy worker nodesmcp__flow-nexus__neural_node_deploy({  cluster_id: "cluster_xyz789",  node_type: "worker",  model: "xl",  role: "worker",  capabilities: ["training", "inference"],  layers: [    { type: "transformer_encoder", num_heads: 16 },    { type: "feed_forward", units: 4096 }  ],  autonomy: 0.9})
// Deploy aggregatormcp__flow-nexus__neural_node_deploy({  cluster_id: "cluster_xyz789",  node_type: "aggregator",  model: "large",  capabilities: ["gradient_aggregation", "model_synchronization"]})
Connect Cluster Topology
javascript
mcp__flow-nexus__neural_cluster_connect({  cluster_id: "cluster_xyz789",  topology: "mesh" // Override default if needed})
Start Distributed Training
javascript
mcp__flow-nexus__neural_train_distributed({  cluster_id: "cluster_xyz789",  dataset: "imagenet", // or custom dataset identifier  epochs: 100,  batch_size: 128,  learning_rate: 0.001,  optimizer: "adam", // sgd, rmsprop, adagrad  federated: true // Enable federated learning})

Federated Learning Example:

javascript
mcp__flow-nexus__neural_train_distributed({  cluster_id: "cluster_xyz789",  dataset: "medical_images_distributed",  epochs: 200,  batch_size: 64,  learning_rate: 0.0001,  optimizer: "adam",  federated: true, // Data stays on local nodes  aggregation_rounds: 50,  min_nodes_per_round: 5})
Monitor Cluster Status
javascript
mcp__flow-nexus__neural_cluster_status({  cluster_id: "cluster_xyz789"})

Response:

json
{  "cluster_id": "cluster_xyz789",  "status": "training",  "nodes": [    {      "node_id": "node_001",      "type": "parameter_server",      "status": "active",      "cpu_usage": 0.75,      "memory_usage": 0.82    },    {      "node_id": "node_002",      "type": "worker",      "status": "active",      "training_progress": 0.45    }  ],  "training_metrics": {    "current_epoch": 45,    "total_epochs": 100,    "loss": 0.234,    "accuracy": 0.891  }}
Run Distributed Inference
javascript
mcp__flow-nexus__neural_predict_distributed({  cluster_id: "cluster_xyz789",  input_data: JSON.stringify([    [0.1, 0.2, 0.3],    [0.4, 0.5, 0.6]  ]),  aggregation: "ensemble" // mean, majority, weighted, ensemble})
Terminate Cluster
javascript
mcp__flow-nexus__neural_cluster_terminate({  cluster_id: "cluster_xyz789"})

5. Model Management

List Your Models
javascript
mcp__flow-nexus__neural_list_models({  user_id: "your_user_id",  include_public: true})

Response:

json
{  "models": [    {      "model_id": "model_abc123",      "name": "Custom Classifier v1",      "architecture": "feedforward",      "accuracy": 0.92,      "created_at": "2025-10-15T14:20:00Z",      "status": "trained"    },    {      "model_id": "model_def456",      "name": "LSTM Forecaster",      "architecture": "lstm",      "mse": 0.0045,      "created_at": "2025-10-18T09:15:00Z",      "status": "training"    }  ]}
Check Training Status
javascript
mcp__flow-nexus__neural_training_status({  job_id: "job_training_xyz"})

Response:

json
{  "job_id": "job_training_xyz",  "status": "training",  "progress": 0.67,  "current_epoch": 67,  "total_epochs": 100,  "current_loss": 0.234,  "estimated_completion": "2025-10-19T12:45:00Z"}
Performance Benchmarking
javascript
mcp__flow-nexus__neural_performance_benchmark({  model_id: "model_abc123",  benchmark_type: "comprehensive" // inference, throughput, memory, comprehensive})

Response:

json
{  "model_id": "model_abc123",  "benchmarks": {    "inference_latency_ms": 12.5,    "throughput_qps": 8000,    "memory_usage_mb": 245,    "gpu_utilization": 0.78,    "accuracy": 0.92,    "f1_score": 0.89  },  "timestamp": "2025-10-19T11:00:00Z"}
Create Validation Workflow
javascript
mcp__flow-nexus__neural_validation_workflow({  model_id: "model_abc123",  user_id: "your_user_id",  validation_type: "comprehensive" // performance, accuracy, robustness, comprehensive})

6. Publishing and Marketplace

Publish Model as Template
javascript
mcp__flow-nexus__neural_publish_template({  model_id: "model_abc123",  name: "High-Accuracy Sentiment Classifier",  description: "Fine-tuned BERT model for sentiment analysis with 94% accuracy",  category: "nlp",  price: 0, // 0 for free, or credits amount  user_id: "your_user_id"})
Rate a Template
javascript
mcp__flow-nexus__neural_rate_template({  template_id: "sentiment-analysis-v2",  rating: 5,  review: "Excellent model! Achieved 95% accuracy on my dataset.",  user_id: "your_user_id"})

Common Use Cases

Image Classification with CNN

javascript
// Initialize cluster for large-scale image trainingconst cluster = await mcp__flow-nexus__neural_cluster_init({  name: "image-classification-cluster",  architecture: "cnn",  topology: "hierarchical",  wasmOptimization: true})
// Deploy worker nodesawait mcp__flow-nexus__neural_node_deploy({  cluster_id: cluster.cluster_id,  node_type: "worker",  model: "large",  capabilities: ["training", "data_augmentation"]})
// Start trainingawait mcp__flow-nexus__neural_train_distributed({  cluster_id: cluster.cluster_id,  dataset: "custom_images",  epochs: 100,  batch_size: 64,  learning_rate: 0.001,  optimizer: "adam"})

NLP Sentiment Analysis

javascript
// Use pre-built templateconst deployment = await mcp__flow-nexus__neural_deploy_template({  template_id: "sentiment-analysis-v2",  custom_config: {    training: {      epochs: 30,      batch_size: 16    }  }})
// Run inferenceconst result = await mcp__flow-nexus__neural_predict({  model_id: deployment.model_id,  input: ["This product is amazing!", "Terrible experience."]})

Time Series Forecasting

javascript
// Train LSTM modelconst training = await mcp__flow-nexus__neural_train({  config: {    architecture: {      type: "lstm",      layers: [        { type: "lstm", units: 128, return_sequences: true },        { type: "dropout", rate: 0.2 },        { type: "lstm", units: 64 },        { type: "dense", units: 1 }      ]    },    training: {      epochs: 150,      batch_size: 64,      learning_rate: 0.01,      optimizer: "adam"    }  },  tier: "medium"})
// Monitor progressconst status = await mcp__flow-nexus__neural_training_status({  job_id: training.job_id})

Federated Learning for Privacy

javascript
// Initialize federated clusterconst cluster = await mcp__flow-nexus__neural_cluster_init({  name: "federated-medical-cluster",  architecture: "transformer",  topology: "mesh",  consensus: "proof-of-learning",  daaEnabled: true})
// Deploy nodes across different locationsfor (let i = 0; i < 5; i++) {  await mcp__flow-nexus__neural_node_deploy({    cluster_id: cluster.cluster_id,    node_type: "worker",    model: "large",    autonomy: 0.9  })}
// Train with federated learning (data never leaves nodes)await mcp__flow-nexus__neural_train_distributed({  cluster_id: cluster.cluster_id,  dataset: "medical_records_distributed",  epochs: 200,  federated: true,  aggregation_rounds: 100})

Architecture Patterns

Feedforward Networks

Best for: Classification, regression, simple pattern recognition

javascript
{  type: "feedforward",  layers: [    { type: "dense", units: 256, activation: "relu" },    { type: "dropout", rate: 0.3 },    { type: "dense", units: 128, activation: "relu" },    { type: "dense", units: 10, activation: "softmax" }  ]}

LSTM Networks

Best for: Time series, sequences, forecasting

javascript
{  type: "lstm",  layers: [    { type: "lstm", units: 128, return_sequences: true },    { type: "lstm", units: 64 },    { type: "dense", units: 1 }  ]}

Transformers

Best for: NLP, attention mechanisms, large-scale text

javascript
{  type: "transformer",  layers: [    { type: "embedding", vocab_size: 10000, embedding_dim: 512 },    { type: "transformer_encoder", num_heads: 8, ff_dim: 2048 },    { type: "global_average_pooling" },    { type: "dense", units: 2, activation: "softmax" }  ]}

GANs

Best for: Generative tasks, image synthesis

javascript
{  type: "gan",  generator_layers: [...],  discriminator_layers: [...]}

Autoencoders

Best for: Dimensionality reduction, anomaly detection

javascript
{  type: "autoencoder",  encoder_layers: [    { type: "dense", units: 128, activation: "relu" },    { type: "dense", units: 64, activation: "relu" }  ],  decoder_layers: [    { type: "dense", units: 128, activation: "relu" },    { type: "dense", units: input_dim, activation: "sigmoid" }  ]}

Best Practices

  1. Start Small: Begin with nano or mini tiers for experimentation
  2. Use Templates: Leverage marketplace templates for common tasks
  3. Monitor Training: Check status regularly to catch issues early
  4. Benchmark Models: Always benchmark before production deployment
  5. Distributed Training: Use clusters for large models (>1B parameters)
  6. Federated Learning: Use for privacy-sensitive data
  7. Version Models: Publish successful models as templates for reuse
  8. Validate Thoroughly: Use validation workflows before deployment

Troubleshooting

Training Stalled

javascript
// Check cluster statusconst status = await mcp__flow-nexus__neural_cluster_status({  cluster_id: "cluster_id"})
// Terminate and restart if neededawait mcp__flow-nexus__neural_cluster_terminate({  cluster_id: "cluster_id"})

Low Accuracy

  • Increase epochs
  • Adjust learning rate
  • Add regularization (dropout)
  • Try different optimizer
  • Use data augmentation

Out of Memory

  • Reduce batch size
  • Use smaller model tier
  • Enable gradient accumulation
  • Use distributed training

Related Skills

  • flow-nexus-sandbox - E2B sandbox management
  • flow-nexus-swarm - AI swarm orchestration
  • flow-nexus-workflow - Workflow automation

Resources

Note: Distributed training requires authentication. Register at https://flow-nexus.ruv.io or use npx flow-nexus@latest register.

来源与署名

来源：ruvnet/ruflo位于.claude/skills/flow-nexus-neural提交60de638

许可证： 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架

更多来自 ruvnet/ruflo 的技能

Cron Schedule

ruvnet

使用 CronCreate 安排持久后台工作进程，并提供推荐的 cron 间隔。

DevOps & Cloud74K今天更新

Autopilot Predict

ruvnet

利用 Ruflo 自动驾驶 MCP 工具与已学模式，预测下一步应执行的任务。

AI & Agents74K今天更新

Autopilot Loop

ruvnet

执行一次自主自动驾驶循环：检查状态、完成预测任务、记录日志并安排下次唤醒。

AI & Agents74K今天更新

Worker Integration

ruvnet

协调后台工作进程与专用代理，将触发类型映射到代理并跟踪性能。

AI & Agents74K今天更新

Worker Benchmarks

ruvnet

为 agentic-flow worker 系统运行性能基准测试，并报告延迟、吞吐量和内存指标。

Software Development74K今天更新

Swarm Advanced

ruvnet

指导使用 Claude Flow 进行高级群体编排，覆盖研究、开发、测试与分析工作流。

AI & Agents74K今天更新

更多AI & Agents技能

Ppt Template Creator

anthropics

精选

将用户的 PowerPoint 模板转化为可复用技能，用于生成品牌演示文稿。

AI & Agents39K2周前更新

Skill Development

anthropics

精选

指导创建 Claude Code 插件技能，涵盖结构、描述、渐进式披露与验证。

AI & Agents37K今天更新

Plugin Structure

anthropics

精选

指导 Claude Code 插件的结构、清单与组件布局。

AI & Agents37K今天更新

Command Development

anthropics

精选

指导创建 Claude Code 斜杠命令，涵盖结构、YAML frontmatter、参数与插件功能。

AI & Agents37K今天更新

Claude Md Improver

anthropics

精选

审查仓库中的 CLAUDE.md 文件，评估其质量，并在获得批准后应用有针对性的改进。

AI & Agents37K今天更新

Find Skills

vercel-labs

精选

指导通过 npx skills 命令行工具发现、评估并安装智能体技能。

AI & Agents33K今天更新