How to use Jev Ultrafast (browser-use/jev-ultrafast): 3 use cases

3 use cases

Run a 7 second browser agent and watch every decision

Start the local inspector and see each element table, operation probability and executed action.
- REPO browser-use/jev-ultrafast
- Claude Code
- Codex
- Software and DevOps
- Intermediate
View prompt
```
Set up browser-use/jev-ultrafast locally, start the inspector with uv run jev, run the demo step by step with Choose next, and summarize for each step the operation chosen, its probability and the target element.
```
Script a web task in Python with one natural language goal

Use the Agent class to run any goal on any URL and stream its state from your own script.
- REPO browser-use/jev-ultrafast
- Claude Code
- Codex
- Cursor
- Software and DevOps
- Intermediate
View prompt
```
Write a Python script with browser-use/jev-ultrafast's Agent that opens <url> and pursues the goal <goal>, logs elapsed_ms and status per step, and then independently checks the page to confirm the goal was met before reporting success.
```

Run a verified flight search that never books

Use the bundled Google Flights example to search a route, check the results and save a trace.

View prompt

Using browser-use/jev-ultrafast, run examples/flights.py with --keep-open, then adapt the library example to search one-way flights from <city> to <city> on <date> for one adult in economy. Stop when results are visible and do not select or book anything.

Quick start with Jev Ultrafast

Check you have what it needs: Python with uv; Chrome with remote debugging allowed (connected through Browser Harness, installed by uv sync); TYPESAFE_API_KEY and TEXT_MODEL_API_KEY (an OpenRouter key in the example config).
Open browser-use/jev-ultrafast on GitHub and read the README and license.
Run git clone https://github.com/browser-use/jev-ultrafast.git and cd jev-ultrafast
Run uv sync then cp .env.example .env and add TYPESAFE_API_KEY and TEXT_MODEL_API_KEY
Start the inspector with uv run jev and open http://127.0.0.1:8766
Click Start demo, then Run automatically; use Choose next to pause before each action

These steps come from our top use case, Run a 7 second browser agent and watch every decision, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for browser-use/jev-ultrafast

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Jev Ultrafast alternatives · Best AI repos for Software and DevOps

About this repo

Who it is forDevelopers building fast web agents who want fewer model calls, no screenshots in the loop and a codebase small enough to read.
Why it is hot24k stars, launched 40 days ago, picked up by one AI source we track
LanguagePython
Sourcegithub.com/browser-use/jev-ultrafast · Back to Hot repos

Requirements

Python with uv
Chrome with remote debugging allowed (connected through Browser Harness, installed by uv sync)
TYPESAFE_API_KEY and TEXT_MODEL_API_KEY (an OpenRouter key in the example config)
Live examples make paid API calls

Add this badge to your README

Maintain Jev Ultrafast? Show readers where to find these use cases.

Markdown

[![Use cases on Deduped](https://dedupedai.com/badge/browser-use/jev-ultrafast.svg)](https://dedupedai.com/use-cases/browser-use-jev-ultrafast/?utm_source=github&utm_medium=badge&utm_campaign=browser-use-jev-ultrafast)

HTML

<a href="https://dedupedai.com/use-cases/browser-use-jev-ultrafast/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=browser-use-jev-ultrafast"><img src="https://dedupedai.com/badge/browser-use/jev-ultrafast.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Jev Ultrafast

What is Jev Ultrafast?

Jev Ultrafast is a browser agent from Browser Use with a dynamic, indexed action space. Each page becomes a numbered element table, TypeSafe's Jev picks one operation (CLICK, TYPE_TEXT, SELECT, SCROLL, WAIT, DONE or BLOCKED) and a target in one network round trip, and a small LLM writes text only when the operation is TYPE_TEXT. The README shows a Zurich to London Google Flights search in about 7 seconds. It is an open-source project on GitHub: https://github.com/browser-use/jev-ultrafast.

How do I use Jev Ultrafast?

Run git clone https://github.com/browser-use/jev-ultrafast.git and cd jev-ultrafast; then run uv sync then cp .env.example .env and add TYPESAFE_API_KEY and TEXT_MODEL_API_KEY; start the inspector with uv run jev and open http://127.0.0.1:8766. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Jev Ultrafast for?

Developers building fast web agents who want fewer model calls, no screenshots in the loop and a codebase small enough to read.

What can I do with Jev Ultrafast?

3 use cases so far, for example: Run a 7 second browser agent and watch every decision; Script a web task in Python with one natural language goal; Run a verified flight search that never books. Each has steps and a copy-paste agent prompt.

What do I need to run Jev Ultrafast?

Python with uv; Chrome with remote debugging allowed (connected through Browser Harness, installed by uv sync); TYPESAFE_API_KEY and TEXT_MODEL_API_KEY (an OpenRouter key in the example config); Live examples make paid API calls.

What are alternatives to Jev Ultrafast?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Jev Ultrafast safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.