NeoHub CLI

AI-powered code assistant in your terminal using local Ollama models

Privacy-first AI coding assistant that runs 100% locally. No cloud, no API keys, no data sent anywhere.

✨ Features

• 🔒 100% Private - All processing happens locally on your machine
• ⚡ Lightning Fast - No API latency, instant responses
• 🧠 Smart Model Selection - AI-powered Model Supervisor recommends the best model for each task
• 🚀 Powerful Models - DeepSeek Coder 33B, CodeLlama 34B, and more
• 💬 Interactive Chat - Conversational AI assistance
• ✏️ Code Editing - AI-powered file modifications
• 🔍 Code Analysis - Review, explain, security, performance analysis

🚀 Quick Start

Prerequisites

• Node.js 18+
• Ollama - Install from ollama.ai

Installation

# Install globally
npm install -g @fsfalmansour/neohub-cli

# Verify installation
neohub --version

First Run

# Initialize configuration
neohub init

# Start chatting with AI
neohub chat

📋 Commands

neohub chat

Start an interactive chat session with AI

neohub chat

Example:

You: Explain async/await in JavaScript
AI: Async/await is syntactic sugar for promises...

neohub edit

Edit files with AI assistance

neohub edit -f app.js -i "add error handling"

Example:

# Add error handling to a function
neohub edit -f server.js -i "add try-catch to all async functions"

# Refactor code
neohub edit -f utils.js -i "convert to TypeScript"

# Create backup first
neohub edit -f config.js -i "add validation" --backup

neohub analyze

Analyze code for issues, explanations, or improvements

neohub analyze <path> [--type review|explain|security|performance]

Examples:

# Code review
neohub analyze src/app.js --type review

# Security analysis
neohub analyze . --type security

# Performance analysis
neohub analyze lib/ --type performance

# Explain code
neohub analyze components/Header.tsx --type explain

neohub models

List available Ollama models

neohub models

Output:

📦 Available Models

● deepseek-coder:33b (17.53 GB)
● codellama:34b (17.74 GB)
● qwen2.5-coder:1.5b (0.92 GB)

neohub recommend

Get intelligent model recommendations

neohub recommend

The Model Supervisor analyzes:

• Task type (code generation, review, debugging, etc.)
• Task complexity
• Available models
• Performance history

Recommends the best model for your specific task!

neohub config

Show current configuration

neohub config

neohub completion

Generate shell completion script for tab completion

# Auto-detect your shell
neohub completion

# Specify shell type
neohub completion --shell bash
neohub completion --shell zsh
neohub completion --shell fish

Enable autocomplete:

# Bash - add to ~/.bashrc or ~/.bash_profile
eval "$(neohub completion --shell bash)"

# Zsh - add to ~/.zshrc
eval "$(neohub completion --shell zsh)"

# Fish - add to ~/.config/fish/config.fish
neohub completion --shell fish | source

After enabling, you can:

• Press TAB to complete commands: neohub ch<TAB> → neohub chat
• Press TAB to complete options: neohub analyze --type <TAB> → shows review explain security performance
• Press TAB to complete file paths: neohub edit -f <TAB> → shows available files

neohub analytics

View usage statistics and analytics

# View analytics dashboard
neohub analytics

# Export analytics data
neohub analytics --export

# Clear analytics data
neohub analytics --clear

# Disable/enable tracking
neohub analytics --disable
neohub analytics --enable

Shows:

• Total commands executed
• Success rate
• Average response time
• Most used commands
• Model performance metrics

Privacy: All analytics stored locally, never sent to cloud

neohub search

Search for code patterns across your project

# Basic search
neohub search "function"

# Case-sensitive search
neohub search "MyClass" --case-sensitive

# Regex search
neohub search "class\s+\w+" --regex

# Search with context
neohub search "TODO" --context-lines 5

# Limit results
neohub search "import" --max-results 20

Options:

• -i, --case-sensitive - Case sensitive search
• -w, --whole-word - Match whole words only
• -r, --regex - Use regex pattern
• -p, --path <path> - Directory to search in
• -m, --max-results <number> - Maximum results (default: 100)
• -c, --context-lines <number> - Context lines (default: 2)

Output:

{
  "ollama": {
    "baseUrl": "http://localhost:11434",
    "model": "deepseek-coder:33b",
    "timeout": 60000
  },
  "preferences": {
    "autoContext": true,
    "maxContextFiles": 10
  }
}

🎯 Model Supervisor

NeoHub includes an intelligent Model Supervisor that automatically recommends the best model for each task:

Task-based Recommendations:

• 📝 Code Generation → DeepSeek Coder 33B (better at generating new code)
• 🔍 Code Review → CodeLlama 34B (trained on review patterns)
• ♻️ Refactoring → DeepSeek Coder 33B (understands structure)
• 🐛 Debugging → CodeLlama 34B (better at finding issues)
• 📖 Code Explanation → CodeLlama 34B (natural language strength)
• 🏗️ Architecture → DeepSeek Coder 33B (system design)

🔧 Configuration

Config file location: ~/.config/configstore/neohub.json

Change Ollama URL

# Edit config file or use init
neohub init

Change Default Model

Edit config file:

{
  "ollama": {
    "model": "codellama:34b"
  }
}

📦 Supported Models

NeoHub works with any Ollama model:

Recommended for Coding:

• deepseek-coder:33b - Best for code generation
• codellama:34b - Best for code review/explanation
• qwen2.5-coder:1.5b - Lightweight, fast

Install Models:

ollama pull deepseek-coder:33b
ollama pull codellama:34b

🌟 Use Cases

1. Interactive Coding Assistant

neohub chat
> How do I implement JWT authentication in Express?

2. Bulk Code Analysis

neohub analyze src/ --type security

3. Automated Refactoring

neohub edit -f *.js -i "convert var to const/let"

4. Learning & Exploration

neohub analyze node_modules/react/index.js --type explain

🚀 Why NeoHub?

vs Cloud AI Tools (ChatGPT, Claude, Copilot)

• ✅ Free - No subscription required
• ✅ Private - Code never leaves your machine
• ✅ Offline - Works without internet
• ✅ Unlimited - No rate limits or tokens

vs Other Local AI Tools

• ✅ Model Supervisor - Intelligent model selection
• ✅ Purpose-built - Designed specifically for coding
• ✅ CLI-first - Fast workflow integration
• ✅ Zero config - Works out of the box

🛠️ Requirements

• Node.js: 18+
• Ollama: Latest version
• Disk Space: 2-20GB (depends on models)
• RAM: 8GB minimum (16GB+ recommended for 33B models)

📊 Performance

Typical Response Times:

• Code completion: <1s
• Code review: 2-5s
• Complex refactoring: 5-10s

Times vary based on model size and hardware

🔗 Links

• GitHub: fahadalmansour/NeoHub
• npm: @fsfalmansour/neohub-cli
• Issues: Report a bug

📄 License

MIT © 2025 Fahad Almansour

🙏 Credits

Built with:

• Ollama - Local LLM runtime
• Commander.js - CLI framework
• Inquirer.js - Interactive prompts

Made with ❤️ for developers who value privacy