openjev — 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 TheoLeeCJ · AI Tool · ★ 1.4k

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

🔒 Is openjev safe to install? View the security audit →

Featured in: TypeSafe Jev

About openjev

OpenJev Can we run something like Jev on a 3090 at home? Wow! No waitlist. Run it in your browser today. Same frozen 4B model · same state · same 21 questions · measured separately, aligned at t=0 in the replay Most agent decisions are small: route this, retry that, does the evidence support X? A chat model can answer them, but it spends time generating text that software immediately parses back into an statement. Jev is TypeSafe's closed service for runtime-defined semantic decisions. This project reproduces that interface pattern with open models; it does not reproduce Jev's undisclosed model or training. This baseline reads typed option probabilities directly from a model. No answer sentence, JSON repair, or decoding loop. Quick start Python 3.10+, CUDA, and a GPU that can hold a 4B BF16 model: Run the owned examples: bash CUDAVISIBLEDEVICES=0 openjev-score \ --mode direct \ --model Qwen/Qwen3.5-4B \ --revision 851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a \ --input examples/decisions.jsonl \

Quick Facts

Stars1,405
Forks86
LanguagePython
CategoryAI Tool
LicenseMIT
Quality Score60.0106154438434/100
Open Issues5
Last Updated2026-09-18
Created2026-09-16
Platformspython
Est. Tokens~15k

openjev alternative? Top 6 similar tools

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

  • vision-agent by landing-ai · ⭐ 5.3k

    This tool has been deprecated. Use Agentic Document Extraction instead.

  • axton-obsidian-visual-skills by axtonliu · ⭐ 3.6k

    Visual Skills Pack for Obsidian: generate Canvas, Excalidraw, and Mermaid diagrams from text with Claude Code

  • claudekit-skills by mrgoonie · ⭐ 2.2k

    All powerful skills of ClaudeKit.cc!

  • EDRSilencer by netero1010 · ⭐ 1.9k

    A tool uses Windows Filtering Platform (WFP) to block Endpoint Detection and Response (EDR) agents from report

  • perf-map-agent by jvm-profiling-tools · ⭐ 1.7k

    A java agent to generate method mappings to use with the linux `perf` tool

  • shaping-skills by rjs · ⭐ 1.4k

    Skills I use with Claude for shaping

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is openjev?

openjev is Can we run something like Jev on a 3090 at home?. It is categorized as a AI Tool with 1.4k GitHub stars.

What programming language is openjev written in?

openjev is primarily written in Python.

How do I install or use openjev?

You can find installation instructions and usage details in the openjev GitHub repository at github.com/TheoLeeCJ/openjev. The project has 1.4k stars and 86 forks, indicating an active community.

What license does openjev use?

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

What are the best alternatives to openjev?

The top alternatives to openjev on Agent Skills Hub include vision-agent, axton-obsidian-visual-skills, claudekit-skills. 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 AI Tool tools