#141 · Primary category: AI Agents & Automation

browser-harness

ai-agent browser-agent browser-automation browser-use browser-use-box browser-use-cloud cdp cloud-browser llm persistent-browser playwright telegram-agent vps-agent web-automation

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Project last updated:08/28/26

GitHub Stars

17.2K

Forks

1.7K

Contributors

70

License

MIT

Why we included this project

This thin, editable harness connects an LLM directly to a running Chrome or Chromium instance over a single CDP websocket, so the agent operates the browser you already have open, with your cookies and logins intact. Its self-healing design is the interesting part: when the agent runs into a task it can't finish, it writes the missing helper code or a reusable domain skill into its own workspace, so the same workflow gets easier on subsequent runs. That makes it a good fit for teams automating repetitive web tasks or wiring browser control into coding agents like Claude Code or Codex, where the setup prompt and skill registration get you going quickly. It also works with cloud browsers for headless or stealth deployments, so you're not limited to a single local machine.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category