
Security News
rv Is a New Rust-Powered Ruby Version Manager Inspired by Python's uv
Ruby maintainers from Bundler and rbenv teams are building rv to bring Python uv's speed and unified tooling approach to Ruby development.
flow-nexus
Advanced tools
🚀 AI-Powered Swarm Intelligence Platform - Gamified MCP Development with 70+ Tools
npx flow-nexus
✨ Free Start • 🎮 Gamified Experience • 🚀 Instant Deploy
Flow Nexus is your AI-powered development platform with 70+ MCP tools. Deploy swarms of specialized agents, complete coding challenges, and earn rUv credits while building real applications.
🚀 70+ MCP Tools | 🎮 Earn While Building | 🤖 AI Swarms | 💰 Free Credits |
---|---|---|---|
Complete toolset for AI development | Gamified challenges & rewards | Multi-agent orchestration | 2560 credits to start |
# 1. Initialize Flow Nexus (interactive setup)
npx flow-nexus init
# 2. Choose your setup:
# → Select a template (Basic, Advanced, Enterprise)
# → Create account or login
# → Get your free rUv credits
# 3. Jump into challenges (earn rUv instantly!)
npx flow-nexus challenge
# 3. Select operation mode:
# → 🎮 Gamer Mode - Challenges & tournaments
# → 🛍️ Store Mode - Browse & deploy apps
# → 🤖 Swarm Mode - Orchestrate AI agents
# → 🛠️ MCP Mode - Direct tool access
# → 👑 Queen Seraphina - AI mentor
# Register new account
npx flow-nexus auth register -e pilot@ruv.io -p your-password
# Login to existing account
npx flow-nexus auth login -e pilot@ruv.io -p your-password
# Initialize local config
npx flow-nexus auth init
# Check authentication status
npx flow-nexus auth status
# Run as MCP server (for Claude Desktop)
npx flow-nexus mcp
# Note: MCP server runs silently waiting for Claude Desktop
# It won't show output unless there's an error
# Test if MCP server is working
echo '{"jsonrpc":"2.0","method":"initialize","params":{},"id":1}' | npx flow-nexus mcp
# Should return: {"result":{"protocolVersion":"..."},"jsonrpc":"2.0","id":1}
# Start with specific mode
npx flow-nexus start swarm # Swarm orchestration tools
npx flow-nexus start store # App store & gamification
npx flow-nexus start gamer # Challenges & achievements
npx flow-nexus start dev # Development tools
npx flow-nexus start complete # All 70+ tools (default)
# Start with HTTP server
npx flow-nexus start --http-port 3000
# Main interactive menu
npx flow-nexus
# Swarm management
npx flow-nexus swarm
# Browse challenges
npx flow-nexus challenge
# Manage sandboxes
npx flow-nexus sandbox
# Check credit balance
npx flow-nexus credits
# View templates
npx flow-nexus template
# Browse app store
npx flow-nexus store
# View profile & stats
npx flow-nexus profile
# Check achievements
npx flow-nexus achievements
# View leaderboard
npx flow-nexus leaderboard
# Deploy distributed neural network (NEW)
npx flow-nexus neural deploy --topology mesh --nodes 4
Every MCP tool operation costs rUv credits. Here are the actual costs from the system:
Operation | Cost | Description |
---|---|---|
swarm_init | 3 rUv | Initialize a new swarm |
agent_spawn | 2 rUv/agent | Create specialized agents |
sandbox_create | 1 rUv | Deploy cloud sandbox |
task_orchestrate | 5 rUv | Complex task coordination |
template_deploy | 1-8 rUv | Deploy app templates |
challenge_submit | 0 rUv | FREE - Submit solutions |
Activity | Reward | How To |
---|---|---|
Register | 100 rUv | Sign up for free account |
Complete Challenge | 10-50 rUv | npx flow-nexus challenge |
Publish App | 25 rUv | Share your creations |
5-Star Rating | 50 rUv | Get high ratings on apps |
# Check your balance
npx flow-nexus credits balance
# View pricing tiers
npx flow-nexus credits pricing
// Initialize swarm
mcp__flow-nexus-npm__swarm_init
- topology: "mesh" | "star" | "ring" | "hierarchical"
- maxAgents: 1-100
- strategy: "balanced" | "specialized" | "adaptive"
// Spawn agents
mcp__flow-nexus-npm__agent_spawn
- type: "researcher" | "coder" | "analyst" | "optimizer" | "coordinator"
- capabilities: ["custom", "skills"]
// Orchestrate tasks
mcp__flow-nexus-npm__task_orchestrate
- task: "Your task description"
- strategy: "parallel" | "sequential" | "adaptive"
// Create sandbox
mcp__flow-nexus-npm__sandbox_create
- template: "node" | "python" | "react" | "nextjs" | "claude-code"
- env_vars: { ANTHROPIC_API_KEY: "..." }
// Execute code
mcp__flow-nexus-npm__sandbox_execute
- sandbox_id: "sandbox-id"
- code: "your code"
- language: "javascript" | "python"
Deploy and manage distributed neural networks across E2B sandboxes with DAA-WASM acceleration:
// Initialize a distributed neural cluster
mcp__flow-nexus-npm__neural_cluster_init
- name: "my-neural-cluster"
- topology: "mesh" | "ring" | "star" | "hierarchical"
- architecture: "transformer" | "cnn" | "rnn" | "gnn" | "hybrid"
- wasmOptimization: true // 3.2x performance boost
- daaEnabled: true // Autonomous coordination
- consensus: "proof-of-learning" | "byzantine" | "raft" | "gossip"
// Deploy neural nodes in sandboxes
mcp__flow-nexus-npm__neural_node_deploy
- cluster_id: "cluster-abc-123"
- role: "worker" | "parameter_server" | "aggregator" | "validator"
- model: "base" | "large" | "xl" | "custom"
- capabilities: ["training", "inference"]
- autonomy: 0.8 // DAA autonomy level (0-1)
// Connect nodes with network topology
mcp__flow-nexus-npm__neural_cluster_connect
- cluster_id: "cluster-abc-123"
- topology: "mesh" // Override default if needed
// Start distributed training
mcp__flow-nexus-npm__neural_train_distributed
- cluster_id: "cluster-abc-123"
- dataset: '{"data": [[1,2], [3,4]], "labels": [0, 1]}'
- epochs: 10
- batch_size: 32
- learning_rate: 0.001
- federated: true // Enable federated learning
// Monitor cluster and training status
mcp__flow-nexus-npm__neural_cluster_status
- cluster_id: "cluster-abc-123"
// Run distributed inference
mcp__flow-nexus-npm__neural_predict_distributed
- cluster_id: "cluster-abc-123"
- input_data: '{"features": [1, 2, 3]}'
- aggregation: "ensemble" | "mean" | "majority" | "weighted"
// Cleanup cluster and sandboxes
mcp__flow-nexus-npm__neural_cluster_terminate
- cluster_id: "cluster-abc-123"
Key Features:
// List challenges
mcp__flow-nexus-npm__challenges_list
- difficulty: "beginner" | "intermediate" | "advanced"
// Submit solution
mcp__flow-nexus-npm__challenge_submit
- challenge_id: "challenge-id"
- solution_code: "your solution"
// Check leaderboard
mcp__flow-nexus-npm__leaderboard_get
- type: "global" | "weekly" | "monthly"
// Browse templates
mcp__flow-nexus-npm__template_list
- category: "quickstart" | "specialized" | "enterprise"
// Deploy template
mcp__flow-nexus-npm__template_deploy
- template_name: "nextjs-saas"
- variables: { project_name: "my-app" }
// Publish app
mcp__flow-nexus-npm__app_store_publish_app
- name: "Your App"
- category: "productivity"
- source_code: "..."
CLI Usage:
# Chat with default model (standard: 4 rUv)
npx flow-nexus seraphina "How do I create a swarm?"
# Select specific AI model
npx flow-nexus seraphina -m basic "Quick question" # Haiku (2 rUv)
npx flow-nexus seraphina -m standard "Help me" # Sonnet (4 rUv)
npx flow-nexus seraphina -m premium "Complex task" # Opus (20 rUv)
npx flow-nexus seraphina -m advanced "Long analysis" # Sonnet+ (8 rUv)
# Enable tool execution
npx flow-nexus seraphina --tools "Deploy a test"
# List models and pricing
npx flow-nexus seraphina --list-models
Model Tiers & Pricing (100% markup on all models):
Model | Name | Cost | Description |
---|---|---|---|
🟢 basic | Haiku | 2 rUv | Fast responses for simple queries |
🔵 standard | Sonnet | 4 rUv | Balanced performance (default) |
🟣 premium | Opus | 20 rUv | Maximum intelligence |
🟡 advanced | Sonnet+ | 8 rUv | Extended context |
MCP Usage:
// Chat with AI mentor
mcp__flow-nexus-npm__seraphina_chat
- message: "How do I deploy to AWS?"
- enable_tools: true // Let her execute commands
- model_tier: "standard" // Optional: basic, standard, premium, advanced
Configuration:
# Set default model in .env
SERAPHINA_DEFAULT_MODEL=standard
When you submit a challenge solution, Queen Seraphina's AI Judge System automatically:
Criteria | Weight | What's Evaluated |
---|---|---|
Correctness | 40% | Tests passed, expected output |
Efficiency | 20% | Execution time, memory usage |
Code Quality | 20% | Clean code, best practices |
Innovation | 20% | Creative solutions, clever approaches |
Criteria | Weight | What's Evaluated |
---|---|---|
Coordination | 30% | Agent teamwork effectiveness |
Task Completion | 30% | Success rate of objectives |
Resource Usage | 20% | Cost optimization |
Scalability | 20% | Architecture quality |
The Judge System automatically awards credits when challenges end:
Rank | Base Reward | Bonus | Total |
---|---|---|---|
🥇 1st Place | 100 rUv | +50 | 150 rUv |
🥈 2nd Place | 75 rUv | +30 | 105 rUv |
🥉 3rd Place | 50 rUv | +20 | 70 rUv |
Top 10 | 25 rUv | - | 25 rUv |
Score ≥ 70 | 10 rUv | - | 10 rUv |
Participation | 5 rUv | - | 5 rUv |
Excellence Bonuses:
# Browse available challenges
npx flow-nexus challenge
# Submit your solution
npx flow-nexus challenge submit
# Example submission flow:
1. Select challenge: "REST API with Swarm Integration"
2. Write your solution
3. Submit for judging
4. Queen Seraphina evaluates automatically
5. Receive score and ranking
6. Credits awarded instantly!
// Alice's submission - Score: 85/100 - Rank: #3 - Won: 50 rUv
const express = require('express');
const app = express();
// Basic but functional API
// Bob's submission - Score: 88/100 - Rank: #2 - Won: 75 rUv
import express from 'express';
import { z } from 'zod';
// Enhanced with validation
// Charlie's submission - Score: 92/100 - Rank: #1 - Won: 100 rUv 🏆
const express = require('express');
const { WebSocketServer } = require('ws');
// Production-ready with WebSocket support
// Fastest execution: 800ms
# Global rankings
npx flow-nexus leaderboard
# Challenge-specific
npx flow-nexus leaderboard --challenge "combat_training"
# Your stats
npx flow-nexus stats
npx flow-nexus
# You'll see:
╔════════════════════════════════════════╗
║ 🚀 FLOW NEXUS MAIN MENU ║
╠════════════════════════════════════════╣
║ ║
║ [1] 🎮 Gamer Mode ║
║ [2] 🛍️ Store Mode ║
║ [3] 🤖 Swarm Mode ║
║ [4] 🛠️ MCP Mode ║
║ [5] 👑 Queen Seraphina ║
║ ║
╚════════════════════════════════════════╝
Template | Cost | Description |
---|---|---|
SaaS Starter | 1 rUv | Complete SaaS boilerplate |
AI Chatbot | 1 rUv | ChatGPT-like interface |
E-Commerce | 2 rUv | Full shopping platform |
Admin Panel | 1 rUv | Dashboard with analytics |
Multi-Tenant | 5 rUv | Enterprise SaaS platform |
Marketplace | 5 rUv | Two-sided marketplace |
CRM System | 8 rUv | Customer management |
# List all templates
npx flow-nexus template
# Deploy a template
npx flow-nexus template deploy
# Option 1: Install globally
npm install -g flow-nexus
# Option 2: Use npx (no install needed)
# Just configure Claude Desktop as shown below
For macOS/Linux:
Edit: ~/Library/Application Support/Claude/claude_desktop_config.json
For Windows:
Edit: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"flow-nexus": {
"command": "npx",
"args": ["-y", "flow-nexus@latest", "mcp"],
"env": {
"PATH": "/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin",
"NODE_PATH": "/usr/local/lib/node_modules"
}
}
}
}
Alternative if you installed globally:
{
"mcpServers": {
"flow-nexus": {
"command": "/usr/local/bin/flow-nexus",
"args": ["mcp"]
}
}
}
If you get spawn flow-nexus ENOENT
:
npm config get prefix
# Usually returns: /usr/local or ~/.npm-global
which flow-nexus
# Should return something like: /usr/local/bin/flow-nexus
{
"mcpServers": {
"flow-nexus": {
"command": "/full/path/to/flow-nexus",
"args": ["mcp"]
}
}
}
{
"mcpServers": {
"flow-nexus": {
"command": "npx",
"args": ["-y", "flow-nexus@latest", "mcp"]
}
}
}
Once configured, you can use all 70+ tools directly in Claude:
- swarm_init, agent_spawn, task_orchestrate
- sandbox_create, sandbox_execute, sandbox_list
- challenge_list, challenge_submit, leaderboard_get
- template_list, template_deploy, app_store_publish
- seraphina_chat (AI mentor)
- And 60+ more tools...
# Using MCP tools in Claude Desktop:
1. Initialize swarm: swarm_init with topology "mesh"
2. Spawn agents: agent_spawn type "coder", "tester", "reviewer"
3. Orchestrate task: task_orchestrate "Build REST API"
4. Monitor progress: swarm_status
# Interactive CLI:
npx flow-nexus challenge
# Select a challenge, write solution, earn credits
# Browse available templates
npx flow-nexus template
# Deploy your choice
# Costs 1-8 rUv depending on template
npx flow-nexus profile
# Shows:
- Developer level
- rUv credit balance
- Challenges completed
- Apps published
- Achievement badges
- Global ranking
npx flow-nexus achievements
# Unlock badges for:
- First swarm deployed
- 10 challenges completed
- App with 5-star rating
- 1000 rUv earned
- Top 10 leaderboard
# General help
npx flow-nexus help
# Command-specific help
npx flow-nexus swarm --help
npx flow-nexus challenge --help
# Ask the AI mentor anything
npx flow-nexus chat
# Or use in MCP:
seraphina_chat with message "How do I create a swarm?"
Not enough credits?
# Check balance
npx flow-nexus credits balance
# Complete daily challenge for free credits
npx flow-nexus challenge
MCP not working in Claude?
# Test MCP server
npx flow-nexus mcp
# Should show: "MCP server running on stdio transport"
Authentication issues?
# Check auth status
npx flow-nexus auth status
# Re-login if needed
npx flow-nexus auth login -e your@email.com -p password
npx flow-nexus
One Command. Real Tools. Actual Results.
Built with ❤️ by rUv
FAQs
🚀 AI-Powered Swarm Intelligence Platform - Gamified MCP Development with 70+ Tools
The npm package flow-nexus receives a total of 9,630 weekly downloads. As such, flow-nexus popularity was classified as popular.
We found that flow-nexus demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Ruby maintainers from Bundler and rbenv teams are building rv to bring Python uv's speed and unified tooling approach to Ruby development.
Security News
Following last week’s supply chain attack, Nx published findings on the GitHub Actions exploit and moved npm publishing to Trusted Publishers.
Security News
AGENTS.md is a fast-growing open format giving AI coding agents a shared, predictable way to understand project setup, style, and workflows.