Skip to content
AI News HubLIVE
More
Summary only

Show HN: Resurf – realistic, reproducible test framework for AI browser agents

Resurf is an open-source, deterministic test framework for AI browser agents, providing realistic, stateful, failure-injectable synthetic websites. It overcomes flaky real websites and static HTML benchmarks. v0 includes an e-commerce test site shop_v1, failure-mode modifiers, multiple adapters (browser-use, Stagehand), and trajectory recording.

SourceHacker News AIAuthor: andrew_zhong
Show HN: Resurf – realistic, reproducible test framework for AI browser agents
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions

Summary only

Under the source content permission, this page provides an editorial summary, key points, and a link to the original article.

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Provides a realistic, dynamic, failure-injectable synthetic website environment for systematic testing of AI browser agents
  • Supports failure-mode injection (latency, payment errors, server errors) configurable via YAML modifiers
  • Includes shop_v1 e-commerce test site with adapters for multiple browser agent frameworks
  • Features deterministic reset, trajectory recording, and success evaluation based on database state, no dependency on live websites

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents