Launched this week
Agent Browser
Browser Agents that communicate using ASCII wireframes
123 followers
Browser Agents that communicate using ASCII wireframes
123 followers
Stop wasting tokens on screenshots. Agent Browser helps AI agents browse the web using wireframe snapshots rather than screenshots or DOM dumps.
Agent Browser
Product Hunt
Agent Browser
@curiouskitty The real breaking point is scale. With existing approaches, a single page can cost around 10k tokens, while Agent Browser typically uses only 1k–3k. And browser agents rarely perform just one action. They usually run multi-step workflows. This means Agent Browser can reduce browser operation costs by up to 70–90%. If a full screenshot is ever needed, the agent can still take one, so switching methods doesn’t mean giving anything up.
Trufflow
Where do you see the biggest savings in token usage? Is it for when something is predominantly image heavy?
Agent Browser
@lienchueh When you are building a browser agent, you have two options. Either you need to use screenshots at every step or to use accessibility snapshots. To be able to use screenshots, you need to use a vision model with computer use capabilities (which is costly). So most people started using accessibility snapshots. But accessibility snapshots dumps much more data then needed for agent to work on the page. Agent Browser takes a different path and builds a wireframe from the visible elements in page which saves 70-90% tokens depending on the page. So the savings apply to each page that the agent uses.
This is a cool idea. I'm assuming it's more suited for task automation or extracting information rather than debugging/verifying visual/ui stuff?
Agent Browser
@masikh Thanks! and yes this is primarily for browser automation with AI agents.
AutonomyAI
Great idea, best of luck with the launch :) looks very 1984 hacker vibe :) I love it and the practical applications seem very real especially for scraping etc
Agent Browser
@lev_kerzhner Thanks! It is also capable of filling inputs, clicking buttons etc. with refs.
Ascii wireframes are a cool idea maybe a small visual preview option could help too.
Agent Browser
@reid_anderson3 The library still exposes screenshot tooling, so agent can take a screenshot if needed.