Jev Gallery
← Back to collection

Docs / source reviewed

Jev Agent Control

Select OpenCode agents and decide when to hand work over

How this project uses Jev

Input
The latest request, bounded recent conversation and textual tool results, eligible agent descriptions and any existing summary
Jev decides
Two Choice questions select the next agent and classify work as actionable, awaiting the user or complete
Code executes
Code validates probabilities, confidence and winning margin before switching; completion boundaries can trigger handoff, manual selection pauses routing, and failures or low confidence retain the current selection

Evidence and limitations

MIT license and pinned 0.1.0 implementation reviewed; OpenCode and Jev were not run. Requires OpenCode V2. Conversation and textual tool results go to TypeSafe; length caps are not sensitive-data redaction. Handoff and cycle limits do not prove completion. Its older SDK dependency does not establish support for the new Box primitive.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →

Learn the approach