开发者工具DEVELOPER TOOLS
HybridRobotics/supermimic
让双足机器人用一套模型学会全身动作跟踪。A library for training humanoid robots to track whole-body motion using one differentiable world model.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
让双足机器人模仿人的全身动作
训练一个能预测物理世界的运动模型
回放训练好的机器人运动轨迹
Train a world model and policy for humanoid motion
Play back a trained model to visualize motion tracking
Choose between generalized or maximal coordinate representations
Run training with GPU acceleration via CUDA
上手GET STARTED
curl -LsSf https://astral.sh/uv/install.sh | sh选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -LsSf https://astral.sh/uv/install.sh | sh
安装脚本使用了 curl 管道执行远程脚本(curl -LsSf https://astral.sh/uv/install.sh | sh),这是高风险行为,可能引入恶意代码。建议手动下载并检查脚本后再执行。The install script uses curl to pipe a shell script from the internet, which is a high-risk practice. Verify the source before running.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
11 NOV 202611 NOV 2026
增长GROWTH
+86.7%+86.7%
1.0k → 1.9k stars · 10 个快照1.0k → 1.9k stars · 10 snapshots
状态STATUS
新发布New
质量 BQuality B
项目刚发布两天,代码和论文都已公开,可以第一时间上手实验。Built on mjlab, a differentiable physics simulator
{
"agents": [],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 0,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "dev-tools",
"secondary": null
},
"localRuntime": "install: curl-pipe, git-clone",
"skillMdTotal": 0,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 2,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [],
"scannedSources": [
"readme"
],
"skillMdFetched": 0
}