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 Yinsongxu · LLM Plugin · ★ 387
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is LLM2Jev safe to install? View the security audit →
LLM2Jev: Turn LLMs into Jev-Style Decision Models 简体中文 LLM2Jev adapts local language models to Jev-style structured decisions. It accepts runtime-defined , , and questions and returns typed answers with probabilities. LLM2Jev is an independent open-source project. It is not affiliated with or endorsed by Jev or TypeSafe. Installation Clone the repository: SGLang is the recommended backend on Linux with a supported NVIDIA GPU. It also installs its Transformers dependency: For a Transformers-only environment: For an editable pip installation, use the corresponding extra: After installing with uv, activate the virtual environment: Quick Start Run the SGLang example with a local Hugging Face-compatible causal language model and a supported NVIDIA GPU: The example submits all three supported question types and prints the response as JSON. Question Types : selects one option and returns a probability distribution and confidence. : evalua
| Stars | 387 |
| Forks | 38 |
| Language | Python |
| Category | LLM Plugin |
| License | Apache-2.0 |
| Quality Score | 67.1920979487492/100 |
| Last Updated | 2026-09-26 |
| Created | 2026-09-19 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with LLM2Jev for enhanced workflows:
Looking for a LLM2Jev alternative? If you're comparing LLM2Jev 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.
Get FAR MORE done with FAR FEWER tokens 🔥
A curated collection of resources, tools, and frameworks for developing GUI Agents.
A curated list of official resources and community projects for TypeSafe, System One models, and Jev.
Jev-compatible API endpoint based on open models (prefill-only)
The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across
Official Microsoft Learn MCP Server and CLI tool – powering LLMs and AI agents with real-time, trusted Microso
Explore other popular llm plugin tools:
LLM2Jev is Turn local language models into Jev-style structured decision models. Get results from text and images with prefill alone—no token-by-token decoding required.. It is categorized as a LLM Plugin with 387 GitHub stars.
LLM2Jev is primarily written in Python. It covers topics such as jev, llm, mllm.
You can find installation instructions and usage details in the LLM2Jev GitHub repository at github.com/Yinsongxu/LLM2Jev. The project has 387 stars and 38 forks, indicating an active community.
LLM2Jev is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to LLM2Jev on Agent Skills Hub include distill, Awesome-GUI-Agents, awesome-typesafe. 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: