Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
LAYA-RLCD
๐ฎ Play. Learn. Respawn. Turn LAYA & ModernBERT Decoder into tactical AI pilots in Cinder Station, an original Doom-inspired game. Explore RLCD + CE, TypeSafe Jev, interactive lessons & transparent benchmarks. Train locally or in Colab. Fork it. Train it. Play it.
Project facts
- Relationship to Jev
- Research
- Evidence
- Documented
- Language
- Jupyter Notebook
- License
- Apache-2.0
- Origin
- Original repository
- Repository status
- Not archived
- Created
- 2026-09-23
- GitHub stars
- 0
- Evidence checked
- 2026-09-24T08:40:10.508Z
- Metadata checked
- 2026-09-24T08:40:10.508Z
- Check status
- current
Stars measure the whole repository, including work unrelated to Jev.
Evidence and scope
Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.
Select **Jev ยท TypeSafe** in the menu. This sends the synthetic game state and action question to TypeSafe and uses your account. Keys stay on the local server. The default model is `jev-1.13.0`; service availability may change. Read the [Jev guide] for the API shape and a tiny client example.
Evidence commit: 822a5a5ac278682bf4adc4a0f63814b70298be9b
Discovered through: github-search.
How we review โ