Learnix

Learnix is an adaptive AI learning ecosystem manager built on Qwen Code, specifically designed to orchestrate personalized learning experiences across any domain. Rather than simply delivering content, Learnix manages your entire learning journey by tracking context, energy, readiness, and curiosity to optimize understanding through discovery and experimentation.

🧠 Autonomous Learning Memory System

Learnix features an autonomous learning memory system that learns about you as you learn:

• Automatic Context Detection: Tracks your energy levels, session types, and focus states
• Learning Pattern Recognition: Identifies your breakthroughs, confusions, and preferences
• Adaptive Memory Capture: Selectively saves important learning insights without manual intervention
• Contextual Recall: Provides relevant past learning experiences to enhance current sessions
• Zero-Configuration: Works automatically in the background - no setup required

How It Works

# Learnix automatically captures and learns from interactions like:
> I'm confused about how async/await works
# → Captures confusion pattern and energy state

> Ah! Now I understand - the await pauses execution
# → Detects breakthrough moment and saves insight

> I prefer learning with concrete examples
# → Records learning preference for future sessions

All learning insights are automatically stored in ~/.learnix/LEARNIX.md and used to personalize future interactions.

🎯 Adaptive Learning Features

Discovery-Driven Learning

• Start with Questions: Begin with "what does this need to accomplish?" rather than explanations
• Guide Experimentation: Let you discover concepts through hands-on exploration
• Natural Mistake Learning: Allow errors to reveal understanding gaps organically

Micro-Step Progression

• One Concept Per Interaction: Focus deeply on single ideas before advancing
• Immediate Validation: Test understanding after each micro-step
• Incremental Building: Layer complexity gradually through proven foundations

Context-Aware Sessions

• Energy-Appropriate Content: Heavy theory when fresh, clarification when tired
• Flexible Pacing: Adjust between quick concepts and intensive deep-dives
• Curiosity Management: Channel tangential interests into deeper understanding

💡 Free Options Available

Get started with Learnix at no cost using any of these free options:

🔥 Qwen OAuth (Recommended)

• 2,000 requests per day with no token limits
• 60 requests per minute rate limit
• Simply run learnix and authenticate with your qwen.ai account
• Automatic credential management and refresh
• Use /auth command to switch to Qwen OAuth if you have initialized with OpenAI compatible mode

🌏 Regional Free Tiers

• Mainland China: ModelScope offers 2,000 free API calls per day
• International: OpenRouter provides up to 1,000 free API calls per day worldwide

For detailed setup instructions, see Authorization.

[!WARNING] Token Usage Notice: Learnix may issue multiple API calls per cycle, resulting in higher token usage (similar to Claude Code). We're actively optimizing API efficiency.

Key Features

• Adaptive Learning Management - Personalized learning experiences that adapt to your style and pace
• Autonomous Memory System - Automatically captures and recalls learning insights
• Code Understanding & Editing - Query and edit large codebases beyond traditional context window limits
• Workflow Automation - Automate operational tasks like handling pull requests and complex rebases
• Enhanced Parser - Adapted parser specifically optimized for Qwen-Coder models
• Context-Aware Sessions - Adapts content delivery to your current energy and focus level

Installation

Prerequisites

Ensure you have Node.js version 20 or higher installed.

curl -qL https://www.npmjs.com/install.sh | sh

Install from npm

npm install -g learnix@latest
learnix --version

Install from source

git clone https://github.com/reny1cao/learnix.git
cd learnix
npm install
npm install -g .

Quick Start

# Start Learnix
learnix

# Example learning-focused commands
> I want to understand how this codebase works
> Help me learn React hooks step by step
> I'm confused about this algorithm - can you break it down?
> Show me how to build this feature, but let me try first

Learnix will automatically:

• Detect your energy level and adapt the explanation depth
• Remember your learning preferences for future sessions
• Track concepts you've mastered vs. those you're still learning
• Provide contextual hints based on your past interactions

Session Management

Control your token usage with configurable session limits to optimize costs and performance.

Configure Session Token Limit

Create or edit .learnix/settings.json in your home directory:

{
  "sessionTokenLimit": 32000
}

Session Commands

• /compress - Compress conversation history to continue within token limits
• /clear - Clear all conversation history and start fresh (keeps learning memory)
• /stats - Check current token usage and limits
• /memory - View your recent learning insights

📝 Note: Session token limit applies to a single conversation, not cumulative API calls. Your learning memory persists across sessions.

Authorization

Choose your preferred authentication method based on your needs:

1. Qwen OAuth (🚀 Recommended - Start in 30 seconds)

The easiest way to get started - completely free with generous quotas:

# Just run this command and follow the browser authentication
learnix

What happens:

1. Instant Setup: CLI opens your browser automatically
2. One-Click Login: Authenticate with your qwen.ai account
3. Automatic Management: Credentials cached locally for future use
4. No Configuration: Zero setup required - just start learning!

Free Tier Benefits:

• ✅ 2,000 requests/day (no token counting needed)
• ✅ 60 requests/minute rate limit
• ✅ Automatic credential refresh
• ✅ Zero cost for individual users
• ✅ Autonomous learning memory included
• ℹ️ Note: Model fallback may occur to maintain service quality

2. OpenAI-Compatible API

Use API keys for OpenAI or other compatible providers:

Configuration Methods:

1. Environment Variables

   export OPENAI_API_KEY="your_api_key_here"
   export OPENAI_BASE_URL="your_api_endpoint"
   export OPENAI_MODEL="your_model_choice"

2. Project .env File Create a .env file in your project root:

   OPENAI_API_KEY=your_api_key_here
   OPENAI_BASE_URL=your_api_endpoint
   OPENAI_MODEL=your_model_choice

API Provider Options

⚠️ Regional Notice:

• Mainland China: Use Alibaba Cloud Bailian or ModelScope
• International: Use Alibaba Cloud ModelStudio or OpenRouter

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus"

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://api-inference.modelscope.cn/v1"
export OPENAI_MODEL="Qwen/Qwen3-Coder-480B-A35B-Instruct"

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus"

export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://openrouter.ai/api/v1"
export OPENAI_MODEL="qwen/qwen3-coder:free"

Learning-Focused Usage Examples

🎓 Discovery-Based Learning

cd your-project/
learnix

# Let Learnix guide you through discovery
> I want to understand this codebase, but I learn better by exploring
> What questions should I be asking about this architecture?
> Let me try to guess what this function does before you explain it

🔍 Adaptive Code Learning

# Learnix adapts to your energy and focus level
> I'm tired but need to understand this quickly
> I have 2 hours to deep dive into React hooks
> I'm curious about how authentication works here

💡 Contextual Learning Assistance

# Based on your learning memory, Learnix might say:
> I remember you prefer visual examples - let me show you...
> Since you struggled with async patterns before, let's start slowly...
> You mentioned you like hands-on learning - try implementing this...

🧪 Experimentation-Driven Development

# Let Learnix guide you through trial-and-error learning
> I want to build a REST API but learn by doing
> What would happen if I changed this component structure?
> Help me understand by breaking something and fixing it

Autonomous Learning Memory

Learnix automatically tracks and learns from your interactions:

What Gets Remembered

• Breakthrough Moments: "Ah! Now I understand..."
• Learning Preferences: "I prefer concrete examples"
• Confusion Patterns: "I always struggle with async concepts"
• Effective Methods: "Step-by-step breakdowns work well for me"
• Energy & Context: Times when you're focused vs. tired

Debug Learning Memory

Enable debug mode to see the learning system in action:

DEBUG=1 learnix

This will show you when learning insights are captured and how they influence responses.

Memory File Location

Your learning insights are stored in:

• Linux/Mac: ~/.learnix/LEARNIX.md
• Windows: %USERPROFILE%\.learnix\LEARNIX.md

You can view this file to see what Learnix has learned about your learning patterns.

Commands & Shortcuts

Session Commands

• /help - Display available commands
• /clear - Clear conversation history (keeps learning memory)
• /compress - Compress history to save tokens
• /stats - Show current session information
• /memory - View recent learning insights
• /auth - Switch authentication methods
• /exit or /quit - Exit Learnix

Keyboard Shortcuts

• Ctrl+C - Cancel current operation
• Ctrl+D - Exit (on empty line)
• Up/Down - Navigate command history

Development & Contributing

Learnix is based on Qwen Code with significant enhancements for adaptive learning.

See CONTRIBUTING.md to learn how to contribute to the project.

For detailed authentication setup, see the authentication guide.

Troubleshooting

If you encounter issues, check the troubleshooting guide.

Learning Memory Issues

If learning memory isn't working as expected:

1. Check permissions: Ensure Learnix can write to ~/.learnix/
2. Enable debug mode: Run with DEBUG=1 learnix to see memory operations
3. Check memory file: View ~/.learnix/LEARNIX.md to see captured insights

Acknowledgments

This project is built upon the excellent work of:

• Qwen Code - The foundation AI workflow tool
• Google Gemini CLI - Original CLI architecture
• Qwen3-Coder - The AI models powering the intelligence

Our main contributions focus on:

• Autonomous Learning Memory System - Automatic capture and recall of learning patterns
• Adaptive Learning Management - Context-aware, personalized learning experiences
• Discovery-Driven Interface - Learning through exploration and experimentation

License

LICENSE