jev-ultrafast
A browser agent that completes web tasks from one goal by picking an action and a page element at each step. It is designed to be fast and cheap, for example booking-style searches on travel sites.
Share on XLicense: MIT
Overview
Jev Ultrafast is a browser agent with an indexed action space. You give it one goal, and at each step TypeSafe's Jev model picks an operation such as click, type text, select or scroll, plus a numbered page element. A small language model writes text only when the operation is TYPE_TEXT. The README shows a Zurich to London search on Google Flights finishing in 7.1 seconds. It runs as a Python library or a local demo with an inspector, and Chrome connects through Browser Harness.
Key features
- Numbered element table built from each page observation
- Operations: click, type text, select, scroll, wait, done, blocked
- Operation and target chosen in one network round trip
- Small LLM writes text only for typing steps
- Python Agent library and local demo inspector
Best for
Developers exploring fast, low-cost web agents that finish tasks from a single goal. It needs a TypeSafe API key and a text model key, and uses Chrome with remote debugging.
- Upstream
- browser-use/jev-ultrafast
- Fork on GitHub
- Guo-astro/jev-ultrafast
- Upstream stars
- 22k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- MIT
- Forked
- 2026-09-17
- Sync status
- In syncLast synced 2026-10-11
More in AI agents and LLM tools
Hello-Agents is a tutorial for learning the principles and practice of AI agents. It guides readers from core concepts to building agent systems and applications.
Forked 2026-10-10Last synced 2026-10-11Custom license (see repository)AI agents and LLM toolsGitHub
OpenSRE is an open-source framework for building AI agents that help investigate production incidents using your infrastructure tools and workflows.
Forked 2026-10-10Last synced 2026-10-11License: Apache-2.0AI agents and LLM toolsGitHub
Context Mode helps AI coding agents use less context and resume work after a conversation is compacted. It is used through MCP and hooks to handle tool output, session memory, and routing across supported platforms.
Forked 2026-10-10Last synced 2026-10-11Custom license (see repository)AI agents and LLM toolsGitHub
ARTEX is a self-hosted AI penetration testing system for exploring assets and reviewing test activity. It brings tasks, findings, asset data and approval steps into one interface.
Forked 2026-10-10Last synced 2026-10-11License: AGPL-3.0AI agents and LLM toolsGitHub