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 2026-09-22, 331 stars and 14 forks when we read it on 2026-11-02. 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.