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 →
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is embodied-jev safe to install? View the security audit →
🤖 EmbodiedJev · 行知 把具身 AI 实验，搬到你的浏览器里。 📦 开箱体验三大仿真任务 · 🧠 本地小模型 / 云端 API · 🎮 看得见的每一步决策 无需机械臂，无需先训练模型。跟着步骤启动，在自己的电脑上体验「观察 → 决策 → 执行 → 反馈」。 🚀 快速上手 · 🧠 接入模型 · 📊 实测结果 · 🤝 一起维护 行而有据，知而能行。 如果这个项目帮你迈出了具身 AI 的第一步，欢迎点一颗 ⭐ Star，让更多人一起玩、一起改！ ✨ 打开行知，你能做什么？ 📦 先玩起来，再接模型：内置规则基线，无需 API Key、GPU 或模型权重，即可运行三个任务。首次安装依赖需要联网。 🦾 真实物理交互：MuJoCo + Franka Panda，夹爪接触、抓取、搬运和放置都有物理反馈。 🧠 模型入口放在界面里：可接 TypeSafe Jev、Claude 原生 API、OpenAI 兼容 API，以及本地 MiniCPM5-2B。 👀 决策过程看得见：查看阶段或短步选择、公开的动作说明、调用次数与延迟；有原生候选概率的接口还会显示概率。 🧭 逐步规划也能试：模型逐轮选择 XYZ 方向、步长和夹爪动作，执行后重新观测；可用原始图像输入并加入中途扰动。 📷 相机自由组合：仅外部、仅腕部、双相机或无相机；启用的视角按动作边界更新，腕部相机随手移动。 🆚 同一任务，不同模型：可选 2–3 路独立实验，统一任务和种子，真实运行后按仿真时间对齐回放。 🧩 按自己的想法扩展：多套具名模型接口、任务/场景预设、JSON 导入导出与独立输入测试，方便二次开发。 🧪 执行前先预演：在仿真副本里检查候
| Stars | 67 |
| Forks | 1 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 57.2340685120468/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-20 |
| Created | 2026-09-20 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with embodied-jev for enhanced workflows:
Looking for a embodied-jev alternative? If you're comparing embodied-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.
Skip to content github / docs Code Issues 80 Pull requests 35 Discussions Actions Projects 2 Security Insights
Skill to talk to Claude about your projects over the phone
.NET MAUI skills for GitHub Copilot and Claude Code
Explore other popular ai tool tools:
embodied-jev is EmbodiedJev: MuJoCo robot decision workbench with MiniCPM5-2B, Jev and compatible model APIs. It is categorized as a AI Tool with 67 GitHub stars.
embodied-jev is primarily written in Python.
You can find installation instructions and usage details in the embodied-jev GitHub repository at github.com/FBddcz/embodied-jev. The project has 67 stars and 1 forks, indicating an active community.
embodied-jev is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to embodied-jev on Agent Skills Hub include redesigned-pancake, claude-code-voice-skill, maui-skills. 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: