agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer
Profile →npx skills add ruvnet/ruflo --skill agent-topology-optimizer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The Topology Optimizer Agent provides dynamic topology reconfiguration, network latency optimization, agent placement optimization, and communication pattern optimization. It aims to improve performance by selecting and migrating to optimal topologies, optimizing physical and routing aspects, placing agents efficiently, and enhancing communication patterns.
How it works
- Dynamic Topology Reconfiguration: The agent maintains multiple topology types (hierarchical, mesh, ring, star, hybrid, adaptive) and uses an analyzer, optimizer, predictor, and various topology generators to evaluate and select an optimal topology. It generates candidates, evaluates them against workload profiles, and selects an optimal topology using multi-objective criteria. If the improvement meets a threshold, it plans and executes a migration, returning a migration plan and estimated downtime.
- Generate Candidates: It creates candidate topologies by iterating through topology types, generating variations, and adding hybrids and AI-generated topologies.
- Multi-objective Evaluation: For each topology, it computes metrics, derives a score, and identifies strengths/weaknesses and suitability.
- Network Latency Optimization: It optimizes physical network placement, routing, protocols, caching, and compression to reduce latency, returning reductions and configurations for each area.
- Physical Optimization: Calculates optimal agent placement, distance reductions, and bandwidth allocation improvements, gathering an expected latency reduction.
- Routing Optimization: Analyzes communication patterns, creates optimal routing tables, enables adaptive routing, and balances load across routes.
- Agent Placement Optimization: Runs multiple placement algorithms in parallel (genetic, simulated annealing, particle swarm, graph partitioning, ML-based), then ensembles results to produce a best placement with score and improvement potential.
- Communication Pattern Optimization: Analyzes historical patterns to optimize batching, protocol selection, compression, caching, and routing. It proposes batching strategies and selects optimal protocols per patterns.
- MCP Integration Hooks: Includes real-time topology optimization, scaling with topology consideration, and coordination optimization hooks that interact with management control plane (MCP) components for monitoring, analysis, and execution of topology changes.
- Neural Network Integration: Provides an AI-powered path with neural models for topology prediction, performance estimation, and pattern recognition, including model loading and prediction calls.
When to use it
Use when you need to dynamically optimize swarm topology for performance, minimize latency, improve routing and placement, or optimize communication patterns based on workload profiles and historical data. It also activates MCP and neural model workflows when AI-assisted topology planning is desired.
What it can touch
- Topology decisions and migration plans (topology selection and migration planning)
- Physical network placement and bandwidth allocation
- Routing tables and adaptive routing mechanisms
- Agent placement decisions across a network
- Communication patterns, batching strategies, and protocol selection
- MCP endpoints for swarm status, performance reports, and topology optimization calls
- Neural topology predictor and performance estimator models (model loading and inference)
Caveats
- License: MIT
- Declared risk/limitations: The skill outlines complex systems with multiple components and AI-assisted components; actual outcomes depend on workload and environment. Some sections show pseudo-implemented code and placeholders (e.g., AI-generated topologies, model loading paths) that require concrete integration work.
--- name: Topology Optimizer type: agent category: optimization description: Dynamic swarm topology reconfiguration and communication pattern optimization --- # Topology Optimizer Agent ## Agent Profile - **Name**: Topology Optimizer - **Type**: Performance Optimization Agent - **Specialization**: Dynamic swarm topology reconfiguration and network optimization - **Performance Focus**: Communication pattern optimization and adaptive network structures ## Core Capabilities ### 1. Dynamic Topology Reconfiguration ```javascript // Advanced topology optimization system class TopologyOptimizer { constructor() { this.topologies = { hierarchical: new HierarchicalTopology(), mesh: new MeshTopology(), ring: new RingTopology(), star: new StarTopology(), hybrid: new HybridTopology(), adaptive: new AdaptiveTopology() }; this.optimizer = new NetworkOptimizer(); this.analyzer = new TopologyAnalyzer(); this.predictor = new TopologyPredictor(); } // Intelligent topology selection and optimization async optimizeTopology(swarm, workloadProfile, constraints = {}) { // Analyze current topology performance const currentAnalysis = await this.analyzer.analyze(swarm.topology); // Generate topology candidat
- Agent Profile
- Core Capabilities
- 1. Dynamic Topology Reconfiguration
- 2. Network Latency Optimization
- 3. Agent Placement Strategies
- 4. Communication Pattern Optimization
- MCP Integration Hooks
- Topology Management Integration
- Neural Network Integration
- Advanced Optimization Algorithms
- 1. Genetic Algorithm for Topology Evolution
- 2. Simulated Annealing for Topology Optimization
- Operational Commands
- Topology Optimization Commands
Analyze current topology npx claude-flow topology-analyze --swarm-id <id> --metrics performance Optimize topology automatically npx claude-flow topology-optimize --swarm-id <id> --strategy adaptive Compare topology configurations npx claude-flow topology-compare --topologies ["hierarchical", "mesh", "hybrid"] Generate topology recommendations npx claude-flow topology-recommend --workload-profile <file> --constraints <file> Monitor topology performance npx claude-flow topology-monitor --swarm-id <id> --interval 60
What does the agent-topology-optimizer skill do?
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer
How do I install it?
Run `npx skills add ruvnet/ruflo --skill agent-topology-optimizer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ruvnet/ruflo, a repository with 67,015 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.