Getting Started
Quickstart
1. Installation
Install the hud SDK:
See Installation for more details on development setup.
2. API Key Setup
Set your API keys in a .env
file:
3. Your First Task
Manual Agent Loop
4. Browser Interaction Patterns
Live Streaming
Browser Use Integration through CDP
5. TaskSet Evaluation
Evaluate your agent on pre-built TaskSets:
6. MCP Telemetry Integration
HUD automatically captures MCP tool calls for debugging:
What’s Captured:
- Tool invocations and responses
- Error states and retries
- Performance data
- Request/response payloads
7. Common Task Patterns
Question Answering
Form Interaction
Spreadsheet Tasks
Response-Only Tasks (No Browser)
Next Steps
- Task Creation Guide: Deep dive into building custom evaluation scenarios
- Custom Environments: Create Docker-based environments for your applications
- Browser Environment: Learn browser-specific features
- Examples: Browse runnable notebooks
Custom Installation & Setup
If you haven’t installed the SDK yet, here’s how:
Standard Installation
Install the HUD SDK using pip:
Requirements
- Python: 3.10 or higher
- API Keys:
HUD_API_KEY
(required for platform features like job/trace uploading, loading remote TaskSets).OPENAI_API_KEY
(optional, required if usingOperatorAgent
or other OpenAI-based agents).ANTHROPIC_API_KEY
(optional, required if usingClaudeAgent
or other Anthropic-based agents).
API Key Configuration
The SDK automatically loads API keys from environment variables or a .env
file located in your project’s root directory.
Create a .env
file in your project root:
Alternatively, export them as environment variables in your shell.
Development Installation (for Contributors)
If you plan to contribute to the SDK or need an editable install:
With the SDK installed and API keys configured, you’re ready to explore all examples and build your own agent evaluations!