COMMUNITY OBSERVEDMetric claims: AUTHOR REPORTEDSOURCE AUDITED🤖 Jev Agent

ego-jev

One ~0.4 s typed decision per DOM step, instead of an LLM turn.

Overview & result

ZephyrDeng shows ego-jev, built on Jev: One ~0.4 s typed decision per DOM step, instead of an LLM turn.

From the original post

ego-jev by @zephyrdeng: One ~0.4 s typed decision per DOM step, instead of an LLM turn.

— ZephyrDeng

How Jev fits in the loop

  1. ego takes a snapshot of the page and numbers the interactive elements.
  2. One System One call picks the operation and its target in the same request.
  3. ego clicks, fills or selects in your real browser, with your sessions and logins.
  4. Free text, screenshots, login, payment and canvas steps go back to the calling agent.

How to reproduce

  1. Review the source documentation and repository at https://github.com/ZephyrDeng/ego-jev.
  2. Configure environment with TypeSafe Jev / System One API keys.
  3. Run test prompts against the decision endpoints.

Why this build matters

Shows Jev in practical use for browser and autonomous agents.

Limitations

  • Jev does not type free text, read screenshots, or touch login, payment or canvas.
  • Timings (about 300–550 ms and about $0.0005 per step) are the author's.
  • Request recording is opt-in and off by default.

Patterns