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 nokia-applied-research · LLM Plugin · ★ 75
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is AnyJev safe to install? View the security audit →
English · 简体中文 · Levels contract · Results · Roadmap Jiamu Zhang1 Tianze Yang1 Yucheng Shi2 Liang Wu1 1 Nokia, Sunnyvale, CA 2 Tencent Hunyuan Qwen3-8B, a real BANKING77 item, real outputs. Left: raw next-token readout — reverse the option
| Stars | 75 |
| Forks | 17 |
| Language | Python |
| Category | LLM Plugin |
| License | Apache-2.0 |
| Quality Score | 63.822438663527/100 |
| Last Updated | 2026-09-22 |
| Created | 2026-09-21 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with AnyJev for enhanced workflows:
Looking for a AnyJev alternative? If you're comparing AnyJev with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisio
805 verified examples of Jev — TypeSafe AI's System One decision model — indexed by the decision each one make
Awesome list of TypeSafe AI Jev use cases: 74 demos ranked by likes, 150+ GitHub repos, limits, cost and API e
🔥🔥 Papers, open reproductions and independent evaluations behind System One models and Jev.
Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (
The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across
Explore other popular llm plugin tools:
AnyJev is Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating). It is categorized as a LLM Plugin with 75 GitHub stars.
AnyJev is primarily written in Python. It covers topics such as calibration, decision-model, jev.
You can find installation instructions and usage details in the AnyJev GitHub repository at github.com/nokia-applied-research/AnyJev. The project has 75 stars and 17 forks, indicating an active community.
AnyJev is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to AnyJev on Agent Skills Hub include open-alternative-jev, awesome-jev, awesome-jev-use-cases. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: