AI/TLDR

browser-use · 2026-04-24 · notable

Browser Harness: Self-Healing LLM Browser Control Directly on CDP

~600-line Python harness giving LLMs direct Chrome DevTools Protocol access for browser automation. Self-healing: when the agent hits a missing capability, it edits helpers.py mid-task to add the function. 6.8K stars, 117 HN points on Show HN.

Browser Harness GitHub repository — minimal CDP-based self-healing browser automation for LLMs

A minimal Python shim (~592 lines) that connects an LLM directly to Chrome via CDP — and lets the agent edit its own harness when it gets stuck.

Key specs

GitHub stars6.8K
Hn points117
Codebase size~592 lines of Python

What is it?

Browser Harness strips away heavyweight abstraction layers (Playwright, Selenium, the browser-use SDK itself) that traditional browser automation frameworks add on top of Chrome. Instead it provides a ~592-line Python shim that speaks the Chrome DevTools Protocol directly over a single WebSocket, plus a small set of helper functions the agent can read and call. The project describes itself as 'the simplest, thinnest, self-healing harness that gives an LLM complete freedom to complete any browser task.'

How does it work?

The harness exposes helper functions as tool calls: navigate, click, type, screenshot, and so on. The unusual part is self-healing: when the LLM encounters a browser interaction the current helper set can't handle, it can write a new helper function and inject it into helpers.py mid-task — effectively extending its own tool API as it runs. All communication flows over CDP WebSocket rather than through a high-level browser framework. A free remote browser tier (cloud.browser-use.com) removes the need to run a local Chrome instance.

Why does it matter?

Most LLM browser automation frameworks ship thousands of lines of deterministic heuristics and hand-tuned selectors that fail on sites the framework authors didn't anticipate. Browser Harness trades that explicit coverage for self-editing adaptability: if the agent doesn't have a tool for a situation, it builds one on the fly. The entire codebase fits in an LLM's context window, which is what makes the self-healing step possible — the agent can actually read and understand what it's modifying.

Who is it for?

Developers building LLM-powered web automation and agent pipelines

Try it

git clone https://github.com/browser-use/browser-harness && pip install -r requirements.txt

Sources · 2 outlets

Tags

  • browser-automation
  • llm-agents
  • cdp
  • self-healing
  • python
  • open-source
  • show-hn
  • agent-tools
  • chrome-devtools
  • computer-use

← All releases · Learn AI