Clado Observe
Project description
Clado Observe
A Python SDK for browser agent observability using Chrome DevTools Protocol (CDP).
Features
- Browser agent observability through Chrome DevTools Protocol
- Integration with Browser Use
- WebSocket-based communication with Chrome instances
- DOM, Network, Screenshot and screencast capabilities
- Vision-Language Model (VLM) evaluation support
Installation
pip install clado-observe
Quick Start
import os
from browser_use.llm import ChatAnthropic
from dotenv import load_dotenv
from clado_observe.agents.browser_use import Agent
load_dotenv()
def main() -> None:
agent = Agent(
task="Find the number of stars of the browser-use repo",
llm=ChatAnthropic(model="claude-sonnet-4-0"),
cdp_url=cdp_url,
api_key=os.getenv("CLADO_API_KEY", ""),
)
agent.run_sync()
if __name__ == "__main__":
main()
Local Development
Testing with Chrome DevTools
To test locally, you need a Chrome DevTools WebSocket debugger URL.
1) Start Chrome with remote debugging enabled
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome \
--remote-debugging-port=9222 \
--user-data-dir=/tmp/chrome-debug
Keep this Chrome instance running while you test.
2) Verify and copy the WebSocket URL
Open http://localhost:9222/json/version in your browser. Find the webSocketDebuggerUrl field and copy its value. It will look like:
ws://localhost:9222/devtools/browser/<some-guid>
3) Set your .env
Create or update .env with your keys and the copied URL:
OPENAI_API_KEY is necessary for the VLM evaluation and another API key is needed in accordance to the browser use environment variable configuration.
ANTHROPIC_API_KEY=sk-...
WEBSOCKET_DEBUGGER_URL=ws://localhost:9222/devtools/browser/<some-guid>
CLADO_API_KEY=cl-...
OPENAI_API_KEY=sk-proj-...
Documentation
For more detailed documentation, please visit https://github.com/clado-ai/observability
License
This project is licensed under the MIT License - see the LICENSE.md file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues and feature requests, please use the GitHub issue tracker.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file clado_observe-0.1.1.tar.gz.
File metadata
- Download URL: clado_observe-0.1.1.tar.gz
- Upload date:
- Size: 232.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3770610f4636f61977c441543a5933b357b72aeccf74f51c70d9afa9342a553f
|
|
| MD5 |
51f0a3de8de73e8661567c6110194fa4
|
|
| BLAKE2b-256 |
2591ec6b4870433cde7bf3ac6e9a18c0b8e5b5744f7cc66967890f60cb12fd9a
|
File details
Details for the file clado_observe-0.1.1-py3-none-any.whl.
File metadata
- Download URL: clado_observe-0.1.1-py3-none-any.whl
- Upload date:
- Size: 28.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3309e0631c69fac4789da57fb3e25cb95220db18eded4e543c696e05a6685c8b
|
|
| MD5 |
d8af795b92e597a06d2757c6f862d701
|
|
| BLAKE2b-256 |
4b3a015ec1f03903a1024ca7364cb47e3550dbb498dceb50b330b6b7c221f3e4
|