by shibing624 · Agent Tool · ★ 12
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
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.
| Stars | 12 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 63/100 |
| Open Issues | 1 |
| Last Updated | 2026-10-21 |
| Created | 2026-10-14 |
| Platforms | python |
| Est. Tokens | ~15k |
Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen 上训练 JEV 风格的 System 1 决策模型。
These tools work well together with train-jev for enhanced workflows:
Looking for a train-jev alternative? If you're comparing train-jev with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated pro
Your SDK solves all of this. One interface. Unified logic. Local + hosted models. Fine-tuning. Agent tools. En
AI-powered text compression library for RAG systems and API calls. Reduce token usage by up to 50-60% while pr
Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language mo
Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as se
Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compa
Explore other popular agent tool tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 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: