embodied-jev

What it is

📦 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

Where the decision sits

embodied-jev calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev.

How active it is

Created 2026-09-20, last pushed 2026-09-20, 89 stars and 1 forks when we read it on 2026-09-20. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.

What we have not checked

Whether it works. We have not run this project, measured the model behind it, or verified any performance claim in its README. This page records what the repository says about itself, read on 2026-09-20. The one model we have measured end to end is Jev.