An AI slop checker tool identifies twelve rules that characterize AI-generated writing, including filler phrases, contrastive negation, hedging, and monotone sentence rhythm. Ten rules are deterministic pattern matches while two use classifiers; the same rules gate articles at seodraft.
effort-router is a Claude Code plugin that automatically selects the appropriate reasoning effort level for each prompt by analyzing the task, conversation history, and code context. It operates in shadow mode for logging recommendations or enforce mode for applying them, using Jev as the default classifier, and requires Claude Code 2.1.283 or later with proper configuration and installation.
Rene-1 is an open-weight 31B parameter classifier model that reads documents and answers multiple typed questions in a single forward pass, returning calibrated probabilities for each option without generating text. The model achieves state-of-the-art results on the Decision Index benchmark, outperforming Jev by 9 points, and runs efficiently on a single GPU using FP8 weight compression.
Jigor is a Rust-based zero-shot classifier gateway supporting multiple backends: von and laya run locally as ONNX models, while jev runs remotely via OpenRouter's Decisions API. It offers a unified wire protocol with installation via npm, pip, or cargo, and can be used ephemerallythrough command-line tools or as a Rust library.
TypeSafe AI released Jev, a fast probabilistic classifier for extracting structured answers from unstructured text, but it lacks true reasoning capabilities compared to symbolic reasoners like Rainbird. Jev works well as a boundary layer between messy language and formal decision systems, though developers must handle complex reasoning logic themselves.
Validator is a CLI tool that compares expected labels with classifier outcomes to identify errors and measure improvements in decision models like Jev. It supports single-label and multi-label classifiers, revealing missed labels and extra flags through metrics like micro-F1 scores.