89 curated builds·evidence labeled
COMMUNITY OBSERVED

Jev-RA Reactive Browser Agent

A fast browser automation loop where Jev decides the next interaction in ~300ms.

Overview & Result

Traditional browser agents pause 3 to 10 seconds per step waiting for multimodal LLMs to output next clicks. Jev-RA decouples visual/DOM parsing from action selection, allowing Jev to pick the next DOM interaction in ~300ms, making browser agents feel interactive.

How Jev fits in the loop

  1. Capture page DOM snapshot and extract interactable candidate elements.
  2. Formulate the next step decision as a choice among actionable elements.
  3. Jev evaluates the candidate set against the immediate sub-goal.
  4. Playwright executes the click/type action and observes the resulting state.

How to reproduce

  1. Clone brnyxx/jev-ra and configure Playwright headless browser.
  2. Define a targeted web exploration task (e.g. item lookup or link verification).
  3. Execute the reactive agent loop and track step execution timing and decision logs.

Why this build matters

Brings reactive latency down to sub-second speeds in browser agents, making practical automation viable.

Reported performance

Reported by author

Latency: ~300 ms per step

Author-reported step latency across standard web task benchmarks.

Limitations

  • Requires reliable DOM selector generation from the underlying page state.
  • Complex multi-page state transitions require an external planner to maintain macro goals.
  • Network delays on heavy sites can outweigh decision latency.

Patterns