Self-healing browser harness via direct CDP

Name: Self-healing browser harness via direct CDP
Availability: InStock
Author: gregpr07

by gregpr07·Apr 20, 2026·3 points·1 comment

Visit Project View on HN

AI Analysis

●●●BangerWizardryBig BrainZero to One

Agent writes missing upload_file() mid-task and commits it — no framework can do this.

Strengths

•Direct CDP connection skips Playwright overhead — ~600 lines total
•Self-healing code generation mid-execution is genuinely novel architecture
•Free tier offers 3 concurrent remote browsers without credit card

Weaknesses

•Browser agent space is crowded with Browser Use, LangChain, and others
•Requires Chrome remote debugging setup — not trivial for all users

Post Description

Creator of browser-use library here.

At Browser Use we spend a lot of time thinking about the bitter lesson of agentic frameworks. A few days we did an experiment that combines replacing Playwright with CDP and giving the LLM complete freedom (building with autoresearch from ground up) to do whatever it knows from pretraining.

I think this is the simplest way to give an AI control of a real browser: raw CDP, and let the agent write its own tools. ~600 lines total.

Example: I forgot to implement upload_file(). Mid-task, the agent noticed, wrote the function, and uploaded the file. I found out when I read the git diff.

I haven't found a task that doesn't work yet - but extremely happy to be proven wrong. Give it a shot. Open to criticism on CDP, agent frameworks, browser use, or whatever.