Prerequisites
- Node.js installed (Download here)
- Comput3 API key (Get yours here)
Installation
1
Install Claude CLI
Install the Claude CLI globally using npm:
You can also use yarn:
yarn global add @anthropic-ai/claude-cli2
Configure Comput3 API
Set up your configuration to use Comput3 as the API provider:
3
Verify Installation
Test the setup with a simple query:
You should see a response powered by Comput3’s GPU infrastructure.
Configuration Options
Environment Variables
Set up environment variables for easier management:- macOS/Linux
- Windows
Add to your shell profile (Then reload your shell:
~/.bashrc, ~/.zshrc, ~/.profile):Configuration File
Create a config file at~/.claude/config.json:
Usage Examples
Basic Chat
Start an interactive conversation:One-time Queries
Ask a single question:Code Analysis
Analyze a code file:Code Generation
Generate code with specific requirements:File Processing
Process multiple files:Advanced Usage
Custom Prompts
Create reusable prompt templates:Piping and Chaining
Chain commands for complex workflows:Batch Processing
Process multiple files with a script:Available Models
Configure different models for different use cases:Code-focused Models
Code-focused Models
Best for: Code generation, debugging, technical explanations
Creative Models
Creative Models
Best for: Documentation, creative writing, brainstorming
Fast Models
Fast Models
Best for: Quick queries, simple tasks
CLI Shortcuts and Aliases
Add these aliases to your shell profile for faster access:Integration with Development Tools
Git Hooks
Add AI-powered git hooks:Editor Integration
Use with your favorite editor:Troubleshooting
Installation Issues
Installation Issues
Common Problems:
- Node.js version compatibility
- Permission issues with global install
- Network connectivity
API Connection Issues
API Connection Issues
Error: “Failed to connect to API”Debug Steps:
Rate Limiting
Rate Limiting
Error: “Rate limit exceeded”Solutions:
- Add delays between requests
- Monitor usage in Comput3 dashboard
- Consider upgrading your plan
Best Practices
Secure API Keys
Store API keys in environment variables, never in scripts or version control.
Efficient Prompting
Be specific and provide context for better results. Include relevant code snippets.
Batch Operations
Group related queries to minimize API calls and improve efficiency.
Error Handling
Always handle API errors gracefully in scripts and automated workflows.
Performance Tips
- Use specific models for different tasks (fast models for simple queries)
- Cache responses for repeated queries
- Limit token usage with appropriate max_tokens settings
- Monitor usage regularly in the Comput3 dashboard