Quick Start

Get drep up and running in 5 minutes. This tutorial walks you through configuration and your first repository scan.

Step 1: Initialize Configuration

Create a configuration file with the interactive setup wizard:

drep init

The wizard will guide you through:

1. Config Location: Choose between current directory or user config directory
2. Platform Selection: Gitea, GitHub, or GitLab
3. Enterprise Servers: Detect and configure GitHub Enterprise, self-hosted GitLab/Gitea
4. Repository Patterns: Use wildcards (owner/*) or specific repos (owner/repo)
5. LLM Backend: OpenAI-compatible (local), AWS Bedrock, or Anthropic
6. Documentation Settings: Enable markdown linting, custom dictionaries
7. Advanced Options: Database URL, LLM temperature, rate limits

$ drep init

============================================================
Welcome to drep configuration setup!
============================================================

Where would you like to store the configuration?
  1. Current directory (./config.yaml) - project-specific
  2. User config directory (~/.config/drep/config.yaml) - system-wide
Choose location [1]:

Which git platform are you using?
Choose platform (github, gitea, gitlab) [github]: github

Using GitHub Enterprise or github.com?
Use custom GitHub server? [y/N]:

Repository Patterns (comma-separated):
Examples: owner/repo, owner/*
Repositories []: owner/my-repo

LLM Provider Selection:
  1. OpenAI-compatible (LM Studio, Ollama, etc.)
  2. AWS Bedrock
  3. Anthropic
Choose provider [1]:

OpenAI-Compatible Configuration:
API Endpoint [http://localhost:1234/v1]:
Model name [qwen3-30b-a3b]:

... (documentation, advanced settings) ...

============================================================
✓ Configuration created successfully!
============================================================

Configuration saved to: ./config.yaml

Next steps:
1. Set GITHUB_TOKEN environment variable
2. Start your LLM server (LM Studio on port 1234)
3. Run: drep scan owner/my-repo

The wizard validates all inputs in real-time and prevents configuration errors before they happen.

Step 2: Configure LLM Backend

Edit config.yaml to point to your LLM server. For LM Studio (default port 1234):

llm:
  enabled: true
  endpoint: http://localhost:1234/v1  # LM Studio
  model: qwen3-30b-a3b
  temperature: 0.2
  max_tokens: 8000
  cache:
    enabled: true
    ttl_days: 30

For Ollama, use http://localhost:11434/v1 as the endpoint.

Step 3: Set Up Platform

Configure your Git platform (Gitea, GitHub, or GitLab). For Gitea:

gitea:
  url: http://localhost:3000
  token: ${GITEA_TOKEN}
  repositories:
    - owner/*  # Monitor all repos for this owner

Set your token as an environment variable:

export GITEA_TOKEN=your_token_here

Step 4: Run Your First Scan

Scan a repository with drep:

# Format: owner/repository
drep scan slb350/drep

# Or scan local path
drep scan /path/to/local/repo

drep will:

1. Clone the repository
2. Analyze all Python files for documentation issues
3. Check code quality and detect potential bugs
4. Create issues in your Git platform with findings

You'll see progress output:

Scanning owner/repository...
✓ Cloned repository
✓ Analyzing documentation (15 files)
✓ Running code quality analysis
✓ Created 3 issues with findings
✓ Scan complete

Understanding Results

drep creates issues in your Git platform for each finding. Issues include:

• Missing docstrings - Public functions/classes without documentation
• Placeholder docstrings - TODOs, FIXMEs, or generic descriptions
• Code quality issues - Bugs, security vulnerabilities, best practice violations
• Markdown quality - Trailing whitespace, broken links, malformed headings (if enabled)

CLI Commands Overview

drep provides several commands for different workflows:

Next Steps

Now that you've run your first scan, explore more features: