User repository on GitHub
A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
A browser-based planetary rover sandbox with a keyless local 3D baseline and an optional selectable TypeSafe controller, where every decision can be inspected, held in teaching mode, saved, replayed and compared against the baseline.
User repository on GitHub
A 3D planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI.
Repo stats from the GitHub API, cached Oct 2026.
A browser-based planetary rover sandbox for experimenting with autonomous decisions using TypeSafe AI. Give a rover a mission, change its environment, and inspect how its choices affect exploration, energy use, and discoveries.
Quoted from the project's README. Read the full README.
Watch out
The README is a running log of numbered tickets under .scratch, so what you get depends on the build: early saved records keep their original five-minute conditions while the expanded world uses eighteen-minute expeditions, and versions 1 through 8 replay under their original rules with missing evidence shown as unavailable. The TypeSafe path is optional and needs your own key, the local Bun backend, and limits you set explicitly. The README states plainly that a different choice from the baseline does not establish a better expedition outcome, and that map inspection, teaching explanations and replay describe recorded route estimates rather than completed results or model reasoning. Copy reviewed against the repository README on 2026-10-04, not from running it.
Original write-ups on what this entry is for.
Posts from builders shipping with Jev right now.