agent-browser: open-source browser automation so agents can verify fixes and file PRs
evilrabbit_ · x · 2026-11-17
The open-source agent-browser project launched a new homepage, pitched as browser automation built for any agent. It lets agents click, type, and screenshot to verify their own work, uses compact snapshots of page controls to cut token usage, and supports 60fps recording, Core Web Vitals performance tests, and network mocking. A demo shows an agent spotting a typo on production, screenshotting it alongside the fixed preview deployment, and pasting both as Before/After into a pull request. The companion agent-desktop extends control into native apps, ready to plug into the coding agent you already use.
More from coding & agent
- WebArena-Pro: multimodal web-agent benchmark with 20 self-hosted apps, best agent at 62.3% — xhluca · 2026-11-17
- Dev shows 'constellation view' UI where every star is a live agent — kevinkern · 2026-11-17
- The constellation view: monitoring agents as stars — green, yellow, red, gray — kevinkern · 2026-11-17
- Directing AI agents by playtesting: one note turned an ugly lighthouse into a beauty — chrisfirst · 2026-11-17
- Dev directs agents with playtest notes to build a game in four days for Epic MegaJam — chrisfirst · 2026-11-17
- 943 agents, 11.5B tokens, $5,900: 97% of tokens went to re-reading context — chrisfirst · 2026-11-17