Quick Start Guide

1 Install Kollabor

If you haven't already, install Kollab CLI using Homebrew:

Or use pip: pip install kollabor

2 Launch Kollabor

Start the application by running:

You'll see the Kollabor welcome screen with the input prompt at the bottom.

3 Configure Your API Key

Kollabor needs an API key to connect to an LLM provider. Set your OpenAI API key:

4 Start Chatting

Type your message and press Enter to send. Kollabor supports:

• Multi-line input (Shift+Enter for new line)
• Conversation history (scroll to review)
• Real-time streaming responses
• Syntax highlighting for code

5 Use Slash Commands

Type / to see available commands:

6 Try Pipe Mode

Use Kollabor in scripts with pipe mode for quick queries:

Or pipe from stdin:

7 Use Agents

Agents are custom configurations with specialized system prompts. Create agents in .kollabor-cli/agents/:

# Create an agent directory
mkdir -p .kollabor-cli/agents/code-reviewer

# Add a system prompt
cat > .kollabor-cli/agents/code-reviewer/system_prompt.md << 'EOF'
You are a code reviewer. Focus on:
- Code quality and best practices
- Potential bugs and edge cases
- Performance considerations
EOF

Switch to your agent:

8 Load Skills

Skills are markdown files that add specific instructions to your agent. Create a skill:

# Add a skill to your agent
cat > .kollabor-cli/agents/code-reviewer/security-check.md << 'EOF'
## Security Check Skill

When reviewing code, also check for:
- SQL injection vulnerabilities
- XSS attack vectors
- Hardcoded secrets or credentials
- Input validation issues
EOF

Load and unload skills dynamically:

9 Explore Plugins

Extend Kollabor with plugins. Create a custom plugin in ~/.kollabor-cli/plugins/:

# my_plugin.py
from core.plugins import BasePlugin

class MyPlugin(BasePlugin):
    def register_hooks(self):
        self.register_hook('pre_user_input', self.my_handler)

    async def my_handler(self, context):
        # Your custom logic here
        return context