Getting Started

Installation

# Clone the repository
git clone https://github.com/Nominate-AI/cbintel.git
cd cbintel

# Install in development mode
pip install -e .

# Install Playwright browsers (for screenshots)
playwright install

Configuration

Create a .env file or set environment variables:

# AI/LLM (required for crawl)
ANTHROPIC_API_KEY=sk-ant-...
OLLAMA_BASE_URL=http://127.0.0.1:11434

# Jobs API (optional)
REDIS_URL=redis://localhost:6379/0
FILES_BASE_URL=https://files.nominate.ai
FILES_API_KEY=...

Quick Start

Web Crawling

# AI-powered research query
cbintel-crawl "What is the current state of AI regulation?"

# With options
cbintel-crawl "AI regulation" --prompt investigative --max-urls 50

Screenshots

# Capture screenshot
cbintel-screenshots screenshot https://example.com -o screenshot.png

# Generate PDF
cbintel-screenshots pdf https://example.com -o document.pdf

Historical Archives

# Discover archived URLs
cbintel-lazarus discover example.com --limit 100

Running Services

Jobs API

# Start directly
cbintel-jobs

# Or via systemd
sudo systemctl start cbjobs

Cluster API

# Start directly
cbintel-cluster

# Or via systemd
sudo systemctl start cbcluster

Next Steps

• Architecture Overview - Understand the system design
• API Reference - Full endpoint documentation