kev
Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference.
34 open source Jev projects in this category, part of AionEdge's independent index of the Jev ecosystem.
Trainable family of small Qwen-based Jev-like decision models with typed primitives, datasets, evaluation tools, and local inference.
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
Open data, training recipe, and a 9B model for Jev-style choice and true/false decisions on Apple Silicon or NVIDIA GPUs.
Local Jev-compatible System One API that converts typed questions into DiffusionGemma classification prompts and probabilities.
Open-model Jev-style server that reads next-token logits to return typed choices, rubric scores, and truth judgments.
The open, local take on Jev: typed decisions from an LLM, without generating a single token
An independent System One decision server compatible with Jev’s API, running an open DiffusionGemma model.
Runs Laya, an open Jev-compatible System One model, from Node.js and TypeScript through ONNX Runtime.
Jev-compatible API server built on open models and SGLang, with prefill-only inference and typed decision endpoints.
Self-hosted Jev-compatible System One server backed by GLiNER-family models, with batching and typed question support.
A router and presets over Convai's Laya checkpoints, packaged as its own engine.
DiffusionGemma NVFP4 structured decisions on a DGX Spark: container recipe No repository-level license file was found during review.
Adapter that turns local language models into Jev-style Choice, Score, and Noul decision engines with typed probabilities.
Approximates the System One contract on top of any logprob-capable model: a fixed answer space, each option scored independently, all questions in parallel.
Open semantic decision engine implementing Choice, Noul, and Score primitives with a TypeSafe comparison harness.
Open Thai-English System One model with Choice inference, calibration, evaluation scripts, and a Jev comparison suite.
A 150M encoder trained to answer typed questions in one pass, with the training notebook written to run on a free GPU.
A 399M bidirectional encoder with one universal choice head, answering Choice, Noul and Score in a single forward pass. Every README figure reconciles to an evaluation JSON shipped in the repository.
Serves DiffusionGemma-Jev behind a compatible API on Cloud Run, with a small game demo on top.
Puts Upstage's Solar Mini4 behind Jev's `/v1/systemone` shape, bring your own Upstage key. Its benchmark grades against a third-party judge rather than a peer model's answers, and every published figure recomputes from the artifacts committed with it.
Research experiment in local System One decisions through llama.cpp logits projection on consumer hardware.
A local server that speaks Jev's `/v1/systemone` shape from a BERT encoder, with a numbered account of every request it refuses that Jev might accept.
Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results.
Small multimodal models for direct decisions on text, documents and images. Its model card publishes the benchmark it loses and states that its confidence field is not a measured probability of correctness. Weights are CC BY-NC-SA.
Training-free Jev-style typed decisions from LLM next-token probabilities. L0 uses cyclic option rotations and label-prior correction to reduce bias without labels; L1 fits temperature calibration using labeled examples. No base-model fine-tuning; calibration and order stability are not universal guarantees.
Asks an Ollama or OpenAI-compatible model to write a likelihood score per candidate, then softmaxes them with a fixed temperature. PolyForm Noncommercial, not an open-source licence.
A local `/v1/systemone` server with two backends: an LFM model zero-shot, and a fine-tuned ModernBERT-Ja cross-encoder. Japanese documentation.
Scores a finite set of choices with a model you already run in llama.cpp and returns a typed decision with a probability distribution.
A CPU port of SemIf that swaps only the model loader and reuses the scoring code unchanged, so you can read a decision out of a small model's option logits on a laptop with no GPU.
Open local System One implementation for NVIDIA DGX Spark, with a Qwen3-based model, Jev-compatible API, architecture notes, and evaluation tooling.
Local Jev-like System One decision layer that returns typed choices and calibrated confidence without a hosted API.
Local Jev-like typed-decision runtime using ONNX and quantized models for offline CPU inference.
OpenJev: an independent Jev-inspired System One decision API based on TypeSafe.ai concepts. Choice, score and noul primitives, local mock server, Python and TypeScript SDKs. Real inference planned; not affiliated with TypeSafe AI. No repository-level license file was found during review.
Local Jev-compatible evaluation server: POST /v1/systemone with typed noul/choice/score, open weights, no waitlist No repository-level license file was found during review.