Reachy Mini 应用、LeRobot 数据集与策略，以及模仿学习台架所依赖的工具 — 由 Hyperion 实验室从开放生态中精选。
精选自 Reachy Mini 与 LeRobot 开放生态的开源内容，另含明确标注的 Hyperion 自有成果。第三方条目并非 Hyperion 产品；每张卡片均链接至其来源与许可证。
Reachy Mini 桌面机器人的官方与社区应用，以及已发布的动作库 — 可从 Hugging Face Spaces 安装。
来自 pollen-robotics
The official voice-conversation app for Reachy Mini, from its maker.
Reachy Mini来自 ravediamond
Community companion app that gives Reachy Mini a baby-like interactive personality.
Reachy Mini来自 8bitkick
Community 3D visualisation of Reachy Mini in the browser.
Reachy Mini来自 mattdotvaughn
Community app that turns Reachy Mini into a language-practice tutor.
Reachy Mini来自 djhui5710
Community bridge app connecting Reachy Mini to a Home Assistant installation.
Reachy Mini来自 pollen-robotics
The official debug and test-bench app for Reachy Mini development.
Reachy Mini来自 8bitkick
Community app for on-device, voice-triggered expressive reactions.
Reachy Mini来自 pollen-robotics
The official radio-player app for Reachy Mini.
Reachy Mini来自 pollen-robotics
The official remote-control app for driving Reachy Mini by hand.
Reachy Mini来自 pollen-robotics
The official step-by-step assembly guide for the Reachy Mini kit.
Reachy Mini来自 pollen-robotics
Curated emotion trajectories for Reachy Mini — JSON moves (head, antennas, body yaw) with audio.
Reachy Mini来自 pollen-robotics
Curated dance trajectories for Reachy Mini, maintained by Pollen Robotics.
Reachy MiniLeRobot 格式的模仿学习数据集与已训练策略 — 从基准仿真到覆盖 SO-100/SO-101 机械臂的跨本体数据集。
来自 lerobot
The PushT manipulation benchmark in LeRobot format — 206 teleop episodes.
sim-only来自 lerobot
The large-scale DROID Franka manipulation dataset in LeRobot v3 format — 95,658 episodes.
Franka来自 lerobot
ALOHA bimanual simulation dataset — human-teleop cube transfer, 50 episodes.
sim-only来自 lerobot
ALOHA bimanual simulation dataset — human-teleop peg insertion, 50 episodes.
sim-only来自 lerobot
Cross-embodiment community pretraining dataset for VLA models — includes SO-100/SO-101 arms.
SO-100SO-101来自 lerobot
The LIBERO benchmark suites in LeRobot format — Panda simulation, 1,693 episodes.
sim-only来自 lerobot
SmolVLA base — the compact open vision-language-action policy for LeRobot.
来自 lerobot
Diffusion Policy trained on PushT — the classic LeRobot dataset/policy baseline pair.
sim-only来自 lerobot
ACT policy trained on the ALOHA cube-transfer dataset.
sim-only来自 lerobot
XVLA base vision-language-action policy in LeRobot format.
来自 lerobot
π0.5 base vision-language-action weights in LeRobot format (Gemma licence terms).
工作栈:LeRobot 库、LeLab 的浏览器工作流，以及 Reachy Mini 应用的官方索引。
来自 lerobot
The open robotics library behind SO-101-class arms — datasets, policies, training and evaluation.
SO-100SO-101Reachy Mini来自 lerobot
Browser UI for LeRobot workflows — teleoperate, record and replay episodes from a local machine.
SO-100SO-101来自 pollen-robotics
The canonical index of Reachy Mini apps, maintained by Pollen Robotics.
Reachy MiniHyperion 台架所运行的 128 GB 统一内存 APU 级别 — 面向本地推理的 AMD Ryzen AI Max+ 395 工具链:llama.cpp 与 vLLM 工具箱、NPU 混合推理服务、基准测试与安装指南。
来自 AMD
The official spec sheet for the Strix Halo APU — 16 Zen 5 cores, Radeon 8060S (40 CU, RDNA 3.5), XDNA 2 NPU (50+ TOPS), up to 128 GB LPDDR5X-8000 unified memory.
Strix Halo来自 kyuz0
The community hub for running local LLMs on Strix Halo — containerised llama.cpp environments per backend, kept current with upstream.
Strix Halo来自 kyuz0
Pre-built llama.cpp toolbox containers for gfx1151 — ROCm and Vulkan backends, rebuilt as llama.cpp master moves.
Strix Halo来自 kyuz0
Toolbx-compatible containers for serving LLMs with vLLM on Strix Halo (gfx1151).
Strix Halo来自 lemonade-sdk
Open-source local LLM server with AMD optimisations — hybrid execution across the XDNA 2 NPU and Radeon GPU on Ryzen AI machines, OpenAI-compatible API.
Strix HaloRyzen AI 300来自 community
Community wiki for local AI on Strix Halo — setup guides including llama.cpp with ROCm.
Strix Halo市场的软件智能体板块 — 专业对话智能体、目录与团队工作流。
每个智能体都建立在 Hyperion 自有的咨询框架之上——而非泛用提示词。
面向企业团队的生产级智能体。
从探索到部署,只需三个简单步骤。
探索我们的专业智能体目录。按类别、能力或使用场景筛选,找到最契合的那一个。
即刻与任意智能体开始对话。测试能力、提出问题,实时查看结果。
将多个智能体组合成项目团队。以协同的 AI 专长编排复杂工作流。
Automatically curate, draft, and send a weekly AI-powered newsletter to your subscriber list using Resend.
Score and prioritize inbound leads every morning using AI enrichment, CRM data, and configurable ICP criteria.
Aggregate top AI news, research papers, and tool releases into a digest delivered to your Slack or email.
Turn client outcomes data into formatted case studies and publish them to your CMS automatically.
Generate, review, and schedule daily blog posts and social content powered by Mistral AI.
Draft a week of LinkedIn posts from your existing content, industry news, or custom prompts — ready for your review.