Frequently Asked Questions

• VS Code: Version 1.80.0 or higher
• Operating System: Windows 10/11, macOS 10.15+, or Linux
• RAM: Minimum 4GB (8GB recommended)
• Internet: Required for AI model access
• Storage: 100MB for extension files

To configure your AI provider:

1. Open VS Code Settings (Ctrl+, or Cmd+,)
2. Search for "LobsAI"
3. Select your preferred AI provider (OpenAI, Anthropic, Google Gemini, etc.)
4. Enter your API key
5. Save settings

Note: API keys are stored locally and encrypted for your security.

LobsAI Coder supports multiple AI providers:

• Anthropic: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
• OpenAI: GPT-4, GPT-4 Turbo, GPT-3.5 Turbo
• Google: Gemini Pro, Gemini Pro Vision
• AWS Bedrock: Various models
• Azure OpenAI: All Azure models
• OpenRouter: Access to 100+ models
• Local Models: Via Ollama or LM Studio

Yes! LobsAI can execute terminal commands with your permission. This includes:

• Installing packages (npm, pip, etc.)
• Running build scripts
• Starting development servers
• Running tests
• Git operations
• Database migrations

All commands require your approval before execution for security.

LobsAI can launch a headless browser to:

• Test web applications
• Debug visual issues
• Capture screenshots
• Monitor console logs
• Perform end-to-end testing
• Interact with UI elements (click, type, scroll)

This is powered by Claude 3.5 Sonnet's Computer Use capability.

Model Context Protocol (MCP) servers allow LobsAI to extend its capabilities through custom tools.

You can:

• Use community-made MCP servers
• Ask LobsAI to create custom tools for your workflow
• Connect to external services (Jira, AWS, databases, etc.)
• Automate repetitive tasks

Example: "Add a tool that fetches Jira tickets" - LobsAI will create and install it automatically!

Yes! All new users get free credits to try LobsAI Coder.

After the trial, you can:

• Use your own API keys (free, pay only to AI provider)
• Purchase credit packages
• Subscribe to monthly plans

Check our Pricing Page for details.

Credits are consumed based on:

• AI Model Usage: Token consumption by the AI model
• Tool Usage: File operations, terminal commands, browser automation
• Context Size: Amount of code/files analyzed

The extension shows real-time credit usage during each task loop.

Absolutely! You can configure your own API keys from:

• OpenAI
• Anthropic
• Google Gemini
• AWS Bedrock
• Azure OpenAI
• OpenRouter

When using your own keys, you pay only the AI provider's rates directly.

LobsAI Coder supports all major programming languages:

Yes! LobsAI is designed for large projects through:

• Smart Context Management: Analyzes file structure and ASTs
• Selective File Reading: Only loads relevant files
• Regex Search: Fast code searches without loading everything
• Progressive Analysis: Breaks down large tasks

This allows LobsAI to handle enterprise-scale projects efficiently.

Partially. LobsAI requires internet for AI model access, but you can:

• Use local models via Ollama or LM Studio (offline)
• View previous conversations offline
• Access cached documentation offline

Note: Most features require internet for optimal performance.

Absolutely. Your code security is our top priority:

• Local Processing: Code is analyzed locally on your machine
• Human-in-the-Loop: All changes require your approval
• Encrypted Storage: API keys encrypted locally
• No Training: Your code is NOT used to train AI models
• Minimal Data Sharing: Only necessary context sent to AI providers

See our Security Page for details.

API keys are:

• Stored locally in VS Code settings
• Encrypted using industry-standard encryption
• Never transmitted to our servers
• Only sent directly to your chosen AI provider

We never have access to your API keys.

Yes. We are fully GDPR compliant:

• Data minimization principles
• User consent management
• Right to access and deletion
• Transparent privacy policies
• Secure data processing

Read our Privacy Policy for full details.