OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Sponsors
These products pay for the directory. Want yours up here?
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
JevalsJevals/jevals-dataIndependent benchmark data comparing TypeSafe AI's Jev (System One model) against LLMs on decision score, accuracy, calibration, cost, and latency for typed tasks.
NearCaiNearCai/JevLightA CityFlow-based traffic signal control framework that evaluates TypeSafe Jev and OpenAI-compatible LLM controllers alongside rule-based and reinforcement-learning baselines through the same simulation pipeline.
LouisUltraLouisUltra/jev-deep-diveAn evidence-graded deep dive into TypeSafe AI's Jev model, covering interface, verification, reproduction comparisons, and a field guide, with runnable probe tools; bilingual EN/中文.
copyleftdevcopyleftdev/jev-labsA research repo that wraps TypeSafe's Jev/System One in a TLA+-verified consensus kernel, with noise-floor measurements, calibration probes, and 1,680 chaos-tested pharmacy decisions via the live Jev API.
DejaAI2DejaAI2/JevNextA learning project that implements a TypeSafe Jev/System One-style decision endpoint on a Qwen3-0.6B backbone with LoRA, plus an OpenAI-compatible chat/generation server and MiniJev-compatible evaluation. Not production software.
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
imom39aimom39a/minesweeper-thinking-labMinesweeper experiments comparing TypeSafe Jev (System One), LLMs, hybrid policies, and deterministic solvers, with documented methods and recorded results.
arifulislamatarifulislamat/jev-benchmarkBenchmarks Jev (typesafe/jev-1.13) via OpenRouter's decisions endpoint, measuring typed decision cost, latency, and accuracy on 100 support tickets against Claude, GPT, and Gemini.
denikucherodenikuchero/jev-chess-labSix recorded chess experiments that call TypeSafe Jev through OpenRouter: independent play, a tactical filter, Stockfish assistance, and a Jev review loop, with full traces, replays, and cost records.
OmniJevOmniJev/PlayJevA multimodal JEV-like model fine-tuned from Qwen3.5-0.8B, playing ten browser games from raw pixels in real time, with demo, training code, and evaluation.
robokrunchrobokrunch/jev-physical-aiReal-world benchmark of TypeSafe's Jev for robot fleets and edge hardware, with 300 measured API calls, cost analysis, and reproducible scripts.
clduab11clduab11/jev-testPre-registered benchmark testing whether TypeSafe Jev's confidence scores reliably decide search, evidence, and citation support for a 2B local model; includes harness, audit tool, and open end-to-end results.
JacobLinCoolJacobLinCool/jev-paper-judgeA paper-review web app and CLI that uses TypeSafe AI's Jev (System One) API to score the understandability and completeness of academic papers in seconds, with a visible rubric and calibration against accepted NeurIPS/ICML papers.
