Local typed decisions with rules, Laya, DistilBERT, and Qwen backends, plus deterministic Hermes and artifact guards.
Local alternatives to Jev — page 8
Independent models and shims that follow the System One interface. They can replace hosted Jev for some workloads; they are not TypeSafe products.
195 active projects in this collection. All collections →
Testing flappy bird with SystemOne Jev like model locally
tiny Jev-like model. Jev and Kev inspired.
Tiny Jev (typesafe) call stub — sample rows + Choice/noul questions
Open, auditable reproduction of TypeSafe Jev: a 2B probabilistic decision model benchmarked across six public suites with weights, code, and receipts.
jevhunt project
Jev-style Choice, Score and Noul decisions from ordinary models. An optional DSH plugin.
Ranks companies by how likely a candidate is to get an interview, with a confidence on each and the mismatch named. Built on TypeSafe's Jev. A shortlist generator, not a prediction.
Jev look like in a very rudimentary way, great for indie hackers.
Hermes Agent middleware using TypeSafe Jev for fail-open deterministic fast paths before LLM execution
No project description available.
AI columns for CSV/JSONL files with TypeSafe's Jev — typed answers, confidence, review queue, resume and cost preview. Local-first, BYO key.
AI coach for Slay the Spire 2 on Steam. Live in-game action recommendations powered by Typesafe Jev through OpenRouter.
No project description available.
No project description available.
No project description available.
Semantic ORDER BY for DuckDB, backed by TypeSafe AI's Jev model. Ships with independent calibration numbers.
Result-based TypeSafe System One client library and jev command-line interface.
A fully audited, reproducible decision‑theoretic mixture‑of‑agents framework comparing multiple selector strategies, including OpenJev, with transparent calibration, limitations, and verification artifacts.
Autonomous evolutionary trading-agent research lab for Solana. Built by Cobalt.
No project description available.
Jax-1-Abel: open-source typed decisions, C++ training/inference and local TypeSafe SDK gateway. Experimental distilled head, not RLCD.
Jev-compatible decision engine over caller-provided models
No project description available.