jevland

SELECTED DEMO PREVIEWS

See it
in use.

15 selected interfaces and recorded runs. Explore a preview, read the evidence, then open the author's demo.

Availability checks: daily · Last pass 541/541 destinations · .

15 demo previews

What was checked →
Support-ticket example with recorded option probabilities in minojev's domain playground.
Recorded minojev decision distributions by zeredy879. Demo screenshot ↗ ·

minojev: a trained decision head on a frozen language model

An independent Jev-style project that freezes a language-model backbone and trains a small decision head over cached candidate features. It publishes typed probability outputs, datasets and browser presentations of its benchmark and game policies.

Link reachable · Demo tested ·
Recorded Snake game with move probabilities and replay controls in the PlayJev gallery.
PlayJev Snake replay by OmniJev, from a recorded episode. Demo screenshot ↗ ·

PlayJev: a 0.8B visual decision model for ten games

An independent Jev-like model fine-tuned from Qwen3.5-0.8B-Base to choose legal actions from raw game frames. The project publishes model weights, training records and a gallery of ten browser games.

Link reachable · Demo tested ·
Saved Clash Royale match with strategy, card probabilities and a decision timeline.
Recorded Clash Royale match and decision probabilities by bytelabs-oss. Demo screenshot ↗ ·

clash-jev: live Clash Royale decisions and recorded replays

A Clash Royale experiment on an Android device that converts screen video into structured game state. Jev selects a strategy, card and placement, while the replay viewer exposes the questions and option probabilities.

Link reachable ·
Recorded candidate decisions and probability labels on JevForge's mock browser surface.
JevForge's recorded Mind2Web candidate replay by zwliJay; API offline during capture. Demo screenshot ↗ ·

JevForge: decision-data synthesis, training and web-action scoring

An end-to-end research toolkit builds decision records, trains and calibrates candidate scorers, and serves a Jev-compatible API. Its released Qwen3.5-0.8B model ranks supplied web actions, while the public demo presents recorded Mind2Web decisions.

Link reachable ·
Luce replay showing ticket queue, priority, anger probabilities and human-review cases.
Recorded ticket triage and review queue by scienthoon; replay, no live inference. Demo screenshot ↗ ·

Luce: train and calibrate a decision model for your task

A task-specific pipeline generates or labels data with an LLM teacher, trains a LoRA and decision head, then evaluates and serves Choice, Score and Noul probabilities. A public support-triage replay shows saved model outputs and review routing.

Link reachable ·
Saved Snake board with three move probabilities and a revealed model choice.
Open-Jev's recorded Snake decision by Zefan-Cai; no live inference. Demo screenshot ↗ ·

Open-Jev: trained decision heads and an inspectable replay workbench

An independent family of LoRA adapters and scalar decision heads returns Choice, Noul and Score outputs over pinned Qwen backbones. The project publishes training data, evaluation records, a CPU classification workbench and interactive saved-decision replays.

Link reachable ·