mini-jev: what a Jev-style typed-decision interface looks like on a frozen Qwen3-4B

by r-ms · AI Tool · ★ 64

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

How to install mini-jev

git clone https://github.com/r-ms/mini-jev.git && cd mini-jev

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 57/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars64
Forks6
LanguagePython
CategoryAI Tool
LicenseMIT
Quality Score57/100
Open Issues2
Last Updated2026-09-18
Created2026-09-17
Platformspython
Est. Tokens~16k

About mini-jev

mini-Jev · read the letter What a Jev-style interface looks like on a frozen model: classify against a schema that arrives with the request by reading next-token logits, not by generating JSON. Measured on Qwen3-4B. TypeSafe's Jev is trained for typed decisions without open generation.

Compatible Skills

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

  • NanoJev — semantic(0.16)+complementary+shared_fw(huggingface)+same_lang+similar_pop+shared_platform (63%)
  • jevmlx — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • openjev-sglang — semantic(0.31)+complementary+shared_fw(huggingface)+same_lang+shared_platform (59%)
  • reflex — semantic(0.44)+shared_fw(huggingface)+same_lang+similar_pop+shared_platform (58%)

mini-jev alternative? Top 3 similar tools

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

  • redesigned-pancake by Sfedfcv · ⭐ 278

    Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights

  • maui-skills by davidortinau · ⭐ 178

    .NET MAUI skills for GitHub Copilot and Claude Code

  • claude-code-voice-skill by abracadabra50 · ⭐ 172

    Skill to talk to Claude about your projects over the phone

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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