jev-visual — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 hr98w · Agent Tool · ★ 163

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

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

About jev-visual

Jev Visual English · 简体中文 A small, runnable project for learning vision-language model inference on Apple Silicon. Use Qwen3.5-0.8B with MLX to answer multiple questions about one image: choose an option, judge yes/no, or score ordered levels. Includes a local browser UI, CLI and HTTP API. This project explores a Jev-like inference pattern for open multimodal language models. It avoids autoregressive structured generation by reusing shared multimodal context and directly scoring candidate outputs from model logits. This is an independent community implementation and does not claim to reproduce TypeSafe Jev's proprietary model architecture, RLCD training, calibration, or serving system. Visual game demos AI sorting factory https://github.com/user-attachments/assets/c87c09d8-30d2-4392-b981-d0b5cf1879ae The factory classifies screenshots of objects on a moving conveyor and selects a sorting lane. The sidebar shows the actual input and candidate probabilities. Breakout https://github.com/user-attachments/assets/a642a6d6-c138-4c02-8378-f2981be22aad Breakout exposes the limits of Qwen3.5-0.8B-4bit in our non-thinking, direct-scoring setup.

Quick Facts

Stars163
Forks21
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score65.1363546339495/100
Last Updated2026-09-18
Created2026-09-17
Platformspython
Est. Tokens~14k

Compatible Skills

These tools work well together with jev-visual for enhanced workflows:

  • vggt-mps — semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (60%)
  • cut-video — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)

jev-visual alternative? Top 3 similar tools

Looking for a jev-visual alternative? If you're comparing jev-visual with other agent tool tools, these 3 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • claude-plugins by Kamalnrf · ⭐ 537

    Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo

  • tutor-skills by RoundTable02 · ⭐ 400

    A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults

  • repren by jlevy · ⭐ 374

    Power rename/refactor tool for CLI and agent use

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is jev-visual?

jev-visual is An educational Jev-like visual inference experiment on Apple Silicon: shared context, direct candidate scoring, and local visual demos.. It is categorized as a Agent Tool with 163 GitHub stars.

What programming language is jev-visual written in?

jev-visual is primarily written in Python.

How do I install or use jev-visual?

You can find installation instructions and usage details in the jev-visual GitHub repository at github.com/hr98w/jev-visual. The project has 163 stars and 21 forks, indicating an active community.

What license does jev-visual use?

jev-visual is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to jev-visual?

The top alternatives to jev-visual on Agent Skills Hub include claude-plugins, tutor-skills, repren. 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