Show HN: A verification browser for AI agents – 13ms windows, one-call checks
A new tool called 'hwatu' has been released to provide verification windows for AI agents, allowing for faster and more reliable agent loops. It integrates with existing coding agents like Claude Code and Cursor to facilitate human-in-the-loop verification.
Why it matters
As AI agents become more autonomous, tools that provide observability and verification are critical for preventing errors and ensuring safe deployment.
Make your agent harness loop instantly faster by giving it real eyes
Vision : durable product principles, native platform strategy, swarm model Agent guide : protocol, primitives, verification loops Human guide : the tiling-WM browser side Benchmarks : every number, measured, with methodology Roadmap : plan of record, priorities, non-goals Continuous improvement : activation metric, feedback loop, weekly cadence Launch kit : reusable copy, channels, and measurement plan Quick Start Install → Detect workflow → Connect agent → Verify page → Hand off to human
curl -fsSL https://raw.githubusercontent.com/hongnoul/hwatu/main/scripts/install.sh | bash hwatu setup One static binary plus your distro's webkitgtk-6.0 (the installer checks). On Arch: yay -S hwatu . From source: cargo build --release .
The installer installs binaries only. hwatu setup detects supported coding agents and prints the available connections without changing their config. Choose a client explicitly when you are ready:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in