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 TianyuCodings · Agent Tool · ★ 1.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is NanoJev safe to install? View the security audit →
NanoJev — A nano replica of Jev English | 简体中文 A 0.6B parallel decision model. States and questions in, complete probability distributions out—with zero output-token decoding. Model · Dataset Open the live side-by-side demo → Three models, one game Download the maze video (MP4) · 27 seconds · 1440 × 1120 · 30 fps Play Snake · Explore the 50×50 maze · Recorded sources and replay checks The standalone ChatGPT Sites demo presents Jev, NanoJev, and Untuned Qwen in three light panels. Playback advances by the same environment step across panels; completed runs freeze at their actual final state. Probability bars show the last decision that produced the displayed state. Shared code planning remains part of each system. The new maze baseline is the original Qwen3-0.6B: 4,726 attempts, 2,044 collisions, goal reached. The older maze video below keeps its original Starting NanoJev comparison and recorded
| Stars | 1,233 |
| Forks | 155 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 59.902743168504/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-20 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with NanoJev for enhanced workflows:
Looking for a NanoJev alternative? If you're comparing NanoJev 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.
Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and
General-purpose Playwright automation for coding agents
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
This repository contains a collection of Agent Skills developed by GudaStudio, enabling seamless collaboration
A collection of standardized Agent Skills to teach GitHub Copilot, Claude, Gemini and Cursor about modern Andr
Explore other popular agent tool tools:
NanoJev is A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.. It is categorized as a Agent Tool with 1.2k GitHub stars.
NanoJev is primarily written in Python.
You can find installation instructions and usage details in the NanoJev GitHub repository at github.com/TianyuCodings/NanoJev. The project has 1.2k stars and 155 forks, indicating an active community.
NanoJev is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to NanoJev on Agent Skills Hub include excalidraw-diagram-skill, raptor, playwright-skill. 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: