CUA-JEV
ZJU-REAL
The [experimental open-task paths](docs/OPEN_TASKS.md) separate model planning from Jev's typed action selection. They discover browser DOM elements or Windows UI Automation controls dynamically and offer grounded structured-tool / physical-GUI alternatives without a site- or app-specific click sequence. A twelve-action browser-to-VS-Code research case now runs end to end with a model and Jev, but **arbitrary-task generalization is not claimed**.
- License
- Not declared
- GitHub Stars
- 11
- Source reviewed
- —
Where Jev makes a decision
Jev returns a structured decision for the local program; consult the source for the exact decision policy.
What this project offers
Adds structured choices or scores to the workflow; performance and cost benefits have not been independently verified.
Review scope
Based on repository metadata and README with rule-based classification; pending human review, with no independent runtime or performance verification.
Sources and implementation
Related projects
jev-ultrafast
browser-use · Browser & OS Action
A browser Agent that uses Jev to choose actions and page controls, calling a text model only when input is needed.
jev-desktop
lahfir · Browser & OS Action
An optional Jev skill for agent-desktop that chooses controls and actions from native accessibility data.
jev-browser
jkudish · Browser & OS Action
Drives a browser from a task and URL, returning the final page, screenshot and action trace.
AskJev
ranjan2829 · Browser & OS Action
Connects Agents to a browser over MCP, using Jev to choose page actions with confirmation gates for actions such as payment or deletion.