Verdict-open-jev — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Heman10x-NGU · Agent Tool · ★ 110

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is Verdict-open-jev safe to install? View the security audit →

About Verdict-open-jev

OpenJev (Verdict): Non-Autoregressive Decision Engine (151M) OpenJev (Verdict) is an open-source, post-trained foundational decision model designed for structured software workflows, inspired by TypeSafe AI\'s Jev and Reinforcement Learning for Calibrated Decisions (RLCD). Instead of generating free-form conversational text that software must parse and validate, OpenJev accepts unstructured input context and evaluates multiple typed questions in a single non-autoregressive forward pass. It returns discrete choices, ordinal scores, and binary probabilities with mathematically calibrated confidence values in under 35 milliseconds. The core thesis: Jevons\' paradox in soft

brier-scorecalibrationdecision-engineedge-aigliclassjevmodernbertonnxrlcdstructured-outputs

Quick Facts

Stars110
Forks14
LanguagePython
CategoryAgent Tool
Quality Score60.3011799567112/100
Open Issues7
Last Updated2026-09-28
Created2026-09-17
Platformsbrowser, python
Est. Tokens~20k

Verdict-open-jev alternative? Top 6 similar tools

Looking for a Verdict-open-jev alternative? If you're comparing Verdict-open-jev with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-jev-gallery by OmniJev · ⭐ 488

    🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System On

  • awesome-jev by OmniJev · ⭐ 65

    🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.

  • jev-dsh-decision by Devin-AXIS · ⭐ 252

    Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。

  • awesome-jev by cobanov · ⭐ 496

    A curated, source-backed list of projects built with Jev, TypeSafe AI's System One model for typed decisions.

  • tinystruct by tinystruct · ⭐ 359

    A lightweight, modular Java application framework for web and CLI development, designed for AI integra

  • awesome-jev by hellogumbo · ⭐ 213

    A community directory of projects built on Jev, TypeSafe AI's System One model.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is Verdict-open-jev?

Verdict-open-jev is Non-autoregressive decision engine on ModernBERT (151M) with calibrated uncertainty (RLCD), TypeSafe AI Jev benchmark audit, and in-browser WebGPU playground. It is categorized as a Agent Tool with 110 GitHub stars.

What programming language is Verdict-open-jev written in?

Verdict-open-jev is primarily written in Python. It covers topics such as brier-score, calibration, decision-engine.

How do I install or use Verdict-open-jev?

You can find installation instructions and usage details in the Verdict-open-jev GitHub repository at github.com/Heman10x-NGU/Verdict-open-jev. The project has 110 stars and 14 forks, indicating an active community.

What are the best alternatives to Verdict-open-jev?

The top alternatives to Verdict-open-jev on Agent Skills Hub include awesome-jev-gallery, awesome-jev, jev-dsh-decision. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools