Get DeepWiki-Open up and running quickly with either Docker (recommended) or manual setup. The fastest way to get started with DeepWiki-Open is using Docker Compose.
1

Clone the Repository

git clone https://github.com/AsyncFuncAI/deepwiki-open.git
cd deepwiki-open
Repository cloned successfully
2

Configure Environment Variables

Create a .env file with your API keys:
.env
# Required: Choose at least one AI provider
GOOGLE_API_KEY=your_google_api_key
OPENAI_API_KEY=your_openai_api_key

# Optional: Additional providers
OPENROUTER_API_KEY=your_openrouter_api_key
AZURE_OPENAI_API_KEY=your_azure_openai_api_key
AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint
AZURE_OPENAI_VERSION=your_azure_openai_version
OLLAMA_HOST=http://localhost:11434
At minimum, you need either GOOGLE_API_KEY or OPENAI_API_KEY to get started.
3

Start with Docker Compose

docker-compose up
This will start both the backend API server (port 8001) and frontend web app (port 3000).
4

Access DeepWiki

Open your browser to http://localhost:3000
You should see the DeepWiki interface ready to generate your first wiki!

​
Manual Setup

For development or custom configurations, you can set up DeepWiki manually.
1

Set Up Environment Variables

Create a .env file in the project root:
GOOGLE_API_KEY=your_google_api_key
OPENAI_API_KEY=your_openai_api_key
2

Start the Backend API

# Install Python dependencies
pip install -r api/requirements.txt

# Start the API server
python -m api.main
The API server will start on port 8001 by default.
3

Start the Frontend

Open a new terminal and run:
npm install
npm run dev
The frontend will be available at http://localhost:3000

​
Generate Your First Wiki

1

Enter Repository URL

In the DeepWiki interface, enter a GitHub, GitLab, or BitBucket repository URL:
  • https://github.com/openai/codex
  • https://github.com/microsoft/autogen
  • https://gitlab.com/gitlab-org/gitlab
  • https://bitbucket.org/redradish/atlassian_app_versions
Start with a smaller repository for your first test to see faster results.
2

Add Access Token (For Private Repos)

If accessing a private repository:
  1. Click ”+ Add access tokens”
  2. Enter your GitHub, GitLab, or BitBucket personal access token
Ensure your token has appropriate repository access permissions.
3

Select AI Model Provider

Choose your preferred AI model provider and model:
  • Default: gpt-4o
  • Also available: o1, o3, o4-mini
  • Best for: High-quality, detailed documentation
  • Access to: Claude, Llama, Mistral, and 100+ models
  • Best for: Trying different models without multiple API keys
4

Generate Wiki

Click “Generate Wiki” and watch the magic happen!
Generation time varies by repository size. Smaller repos take 30 seconds to 2 minutes, while larger ones may take 5-10 minutes.

​
API Key Setup

  1. Visit Google AI Studio
  2. Create a new API key
  3. Add to .env as GOOGLE_API_KEY=your_key_here
Google Gemini offers generous free tier limits and fast performance.

​
Verification

Visit http://localhost:8001/docs to see the FastAPI documentation and test endpoints.
# Test API health
curl http://localhost:8001/health
The frontend at http://localhost:3000 should show:
  • Repository input field
  • Model selection dropdown
  • Generate Wiki button
Check that your environment variables are loaded correctly:
# In the API logs, you should see
python -m api.main
# INFO - Starting Streaming API on port 8001
# No warnings about missing API keys for your chosen provider

​
Next Steps

Learn Core Features

Explore wiki generation, Ask feature, and DeepResearch

Configure Model Providers

Set up multiple AI providers and choose the best models

Deploy to Production

Deploy DeepWiki for production use

API Integration

Integrate DeepWiki into your existing workflows

​
Troubleshooting

  • Ensure the backend is running on port 8001
  • Check firewall settings
  • Verify no other services are using port 8001
  • Check .env file exists in project root
  • Verify API keys are correctly formatted
  • Ensure no extra spaces in environment variables
  • Double-check API key accuracy
  • Verify API key permissions and quotas
  • Test API key with provider’s documentation
For more detailed troubleshooting, see the Troubleshooting Guide.