abdel

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

Natural-language constraints for JEPA world-model planning, judged by a decision model instead of an LLM.

Observable browser stealth game: Jev makes typed guard judgments while deterministic code owns the world.

Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.

Did the agent actually finish? Inspectable GLiNER2.5-Decide fine-tuning on task completion and evidence spans.

Signed, auditable receipts for Gemma 4 inference. The provider commits to the execution trace; an auditor challenges random positions and verifies them on a CPU without the weights: Freivalds checks, exact decode, Merkle-bound traces. CommitLLM protocol.

Redirect legacy Awesome Jev Pages URLs to the current directory

Typed System One layer for Rust (Choice/Score/Noul).

Latency-first Rust SDK for TypeSafe System One.

An inspectable action guard for LLM-driven Reachy Mini apps.

A two-truths-and-a-lie game with probability-driven robot body language.

Realtime social attention and turn-taking for Reachy Mini.

Typed Jev decision primitives for Reachy Mini applications.