> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comput3.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude CLI Setup

> Configure Claude CLI to use Comput3 Network for command-line AI assistance

Set up Claude CLI with Comput3 Network to get AI assistance directly from your terminal.

## Prerequisites

* Node.js installed ([Download here](https://nodejs.org))
* Comput3 API key ([Get yours here](https://app.comput3.ai))

## Installation

<Steps>
  <Step title="Install Claude CLI">
    Install the Claude CLI globally using npm:

    ```bash theme={null}
    npm install -g @anthropic-ai/claude-cli
    ```

    <Note>
      You can also use yarn: `yarn global add @anthropic-ai/claude-cli`
    </Note>
  </Step>

  <Step title="Configure Comput3 API">
    Set up your configuration to use Comput3 as the API provider:

    ```bash theme={null}
    claude config set api-key YOUR_COMPUT3_API_KEY
    claude config set api-base https://api.comput3.ai/v1
    claude config set model hermes4:70b
    ```

    <Warning>
      Replace `YOUR_COMPUT3_API_KEY` with your actual API key from the Comput3 dashboard.
    </Warning>
  </Step>

  <Step title="Verify Installation">
    Test the setup with a simple query:

    ```bash theme={null}
    claude "Hello, can you help me write a Python function?"
    ```

    <Check>
      You should see a response powered by Comput3's GPU infrastructure.
    </Check>
  </Step>
</Steps>

## Configuration Options

### Environment Variables

Set up environment variables for easier management:

<Tabs>
  <Tab title="macOS/Linux">
    Add to your shell profile (`~/.bashrc`, `~/.zshrc`, `~/.profile`):

    ```bash theme={null}
    export ANTHROPIC_API_KEY="your_comput3_api_key"
    export ANTHROPIC_API_BASE="https://api.comput3.ai/v1"
    export CLAUDE_MODEL="hermes4:70b"
    ```

    Then reload your shell:

    ```bash theme={null}
    source ~/.zshrc  # or ~/.bashrc
    ```
  </Tab>

  <Tab title="Windows">
    Set environment variables in PowerShell:

    ```powershell theme={null}
    $env:ANTHROPIC_API_KEY="your_comput3_api_key"
    $env:ANTHROPIC_API_BASE="https://api.comput3.ai/v1"
    $env:CLAUDE_MODEL="hermes4:70b"
    ```

    Or set permanently via System Properties → Environment Variables.
  </Tab>
</Tabs>

### Configuration File

Create a config file at `~/.claude/config.json`:

```json theme={null}
{
  "api_key": "your_comput3_api_key",
  "api_base": "https://api.comput3.ai/v1",
  "model": "hermes4:70b",
  "temperature": 0.7,
  "max_tokens": 4096,
  "timeout": 30000
}
```

## Usage Examples

### Basic Chat

Start an interactive conversation:

```bash theme={null}
claude chat
```

### One-time Queries

Ask a single question:

```bash theme={null}
claude "Explain how async/await works in JavaScript"
```

### Code Analysis

Analyze a code file:

```bash theme={null}
claude "Review this code for potential issues" < script.py
```

### Code Generation

Generate code with specific requirements:

```bash theme={null}
claude "Create a REST API endpoint in Express.js for user authentication"
```

### File Processing

Process multiple files:

```bash theme={null}
find . -name "*.js" -exec claude "Add JSDoc comments to this file" < {} \;
```

## Advanced Usage

### Custom Prompts

Create reusable prompt templates:

```bash theme={null}
# Create a prompt file
echo "You are a senior software engineer. Review the following code and suggest improvements:" > review_prompt.txt

# Use the prompt
claude "$(cat review_prompt.txt)" < my_code.py
```

### Piping and Chaining

Chain commands for complex workflows:

```bash theme={null}
# Generate and review code
claude "Write a Python function to parse JSON" | claude "Review this code for best practices"

# Process git diff
git diff | claude "Summarize the changes in this diff"

# Analyze logs
tail -n 100 app.log | claude "Find any error patterns in these logs"
```

### Batch Processing

Process multiple files with a script:

```bash theme={null}
#!/bin/bash
for file in src/*.js; do
    echo "Processing $file..."
    claude "Add TypeScript types to this JavaScript file" < "$file" > "${file%.js}.ts"
done
```

## Available Models

Configure different models for different use cases:

<AccordionGroup>
  <Accordion title="Code-focused Models">
    **Best for**: Code generation, debugging, technical explanations

    ```bash theme={null}
    claude config set model hermes4:70b
    claude config set temperature 0.2
    ```
  </Accordion>

  <Accordion title="Creative Models">
    **Best for**: Documentation, creative writing, brainstorming

    ```bash theme={null}
    claude config set model hermes4:405b
    claude config set temperature 0.8
    ```
  </Accordion>

  <Accordion title="Fast Models">
    **Best for**: Quick queries, simple tasks

    ```bash theme={null}
    claude config set model kimi-k2
    claude config set temperature 0.5
    ```
  </Accordion>
</AccordionGroup>

## CLI Shortcuts and Aliases

Add these aliases to your shell profile for faster access:

```bash theme={null}
# Quick aliases
alias c="claude"
alias cr="claude 'Review this code:'"
alias ce="claude 'Explain this code:'"
alias cg="claude 'Generate code for:'"

# Function for code review
review() {
    if [ -f "$1" ]; then
        claude "Review this code for bugs and improvements:" < "$1"
    else
        echo "File not found: $1"
    fi
}

# Function for documentation
document() {
    if [ -f "$1" ]; then
        claude "Generate documentation for this code:" < "$1"
    else
        echo "File not found: $1"
    fi
}
```

## Integration with Development Tools

### Git Hooks

Add AI-powered git hooks:

```bash theme={null}
#!/bin/sh
# .git/hooks/pre-commit
git diff --cached | claude "Review these changes for potential issues"
```

### Editor Integration

Use with your favorite editor:

```bash theme={null}
# Vim integration
vnoremap <leader>c :w !claude "Explain this code"<CR>

# Emacs integration  
(defun claude-explain-region ()
  (interactive)
  (shell-command-on-region (region-beginning) (region-end) "claude 'Explain this code'"))
```

## Troubleshooting

<AccordionGroup>
  <Accordion title="Installation Issues">
    **Common Problems**:

    * Node.js version compatibility
    * Permission issues with global install
    * Network connectivity

    **Solutions**:

    ```bash theme={null}
    # Check Node.js version (requires 16+)
    node --version

    # Install with sudo if needed (macOS/Linux)
    sudo npm install -g @anthropic-ai/claude-cli

    # Use npx for one-time usage
    npx @anthropic-ai/claude-cli "your query"
    ```
  </Accordion>

  <Accordion title="API Connection Issues">
    **Error**: "Failed to connect to API"

    **Debug Steps**:

    ```bash theme={null}
    # Test API key
    curl -H "Authorization: Bearer YOUR_API_KEY" https://api.comput3.ai/v1/models

    # Check configuration
    claude config list

    # Test with verbose output
    claude --verbose "test query"
    ```
  </Accordion>

  <Accordion title="Rate Limiting">
    **Error**: "Rate limit exceeded"

    **Solutions**:

    * Add delays between requests
    * Monitor usage in Comput3 dashboard
    * Consider upgrading your plan

    ```bash theme={null}
    # Add delay in scripts
    claude "query 1" && sleep 1 && claude "query 2"
    ```
  </Accordion>
</AccordionGroup>

## Best Practices

<CardGroup cols={2}>
  <Card title="Secure API Keys" icon="key">
    Store API keys in environment variables, never in scripts or version control.
  </Card>

  <Card title="Efficient Prompting" icon="brain">
    Be specific and provide context for better results. Include relevant code snippets.
  </Card>

  <Card title="Batch Operations" icon="layer-group">
    Group related queries to minimize API calls and improve efficiency.
  </Card>

  <Card title="Error Handling" icon="exclamation-triangle">
    Always handle API errors gracefully in scripts and automated workflows.
  </Card>
</CardGroup>

## 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