microduck

🦆🤖 ¡Conocé Microduck! Pequeños robots open source de 25 cm que aprenden a caminar mediante IA y simulaciones. NVIDIA los mostró en la GTC Berlín 2026. 🛠️ Podés explorar su código: pollen-robotics/microduck #IA #Robotica t.co

Microduck Robot: Why Simulation Meets Reality 🦆 #robotics Microduck: the tiny robot behind a big sim-to-real question 🦆🤖 Pollen Robotics trains behaviours in simulation and deploys them to the real robot. That transfer is a real robotics challenge — but the exact cause of a particular stage tumble has not been established. Context for this reel: Microduck had already been demonstrated on real floors before the keynote. Its official training stack uses MuJoCo. The $399 price is introductory, before taxes and shipping; the 20,000 preorder figure should not be read as an independently audited sales total. Open-source software does not by itself mean every hardware/build file is freely available. Explore the official robot and training resources: pollen-robotics.com Comment DUCK if you want to explore the project. Share this with the friend who wants their own robot. #Microduck #Robotics #PhysicalAI #PollenRobotics #ReinforcementLearning Official software: pollen-robotics/microduck Footage: NVIDIA keynote and Pollen Robotics, credited on screen.

That viral Jensen Huang demo with four Microducks? An engineer was piloting each one. Pollen's own @RemiFabreRobot says so. I like it more for that. The pilot says walk or sit. Staying upright is a policy it learned in sim. Open-source code, $399. pollen-robotics/microduck t.co

전세계에서 가장 핫한 깃허브 TOP 8 공개 2026년 10월 25일 GitHub Trending 목록에서 당일 스타 증가 수로 뽑은 프로젝트 8개입니다. AI 목소리 만들기, 웹 디자인 수정, 로봇 제어, 코드 보안 검사까지. 각 도구가 무엇을 하는지 공식 화면과 공개 데모로 살펴봤습니다. 순위 조회: 2026년 10월 25일 22:34 (한국·일본 시간) 범위: Daily / 전체 언어의 Trending 노출 목록. GitHub 전체 저장소를 전수 조사한 순위가 아닙니다. 오늘 증가분과 누적 스타는 별개입니다. ⏱ 타임스탬프 00:00 시작 · TradingAgents 00:37 자미두수 01:06 Microduck 01:33 Cindy 02:03 Impeccable 02:31 Hallmark 03:04 VoiceStudio 03:39 Security Audit Skill 04:19 마무리 🔗 GitHub 프로젝트 1위 · 오늘 +2,874 / 누적 45,953 cloudflare/security-audit-skill 2위 · 오늘 +1,588 / 누적 85,833 debpalash/VoiceStudio 3위 · 오늘 +1,359 / 누적 32,977 Nutlope/hallmark 4위 · 오늘 +1,113 / 누적 87,086 pbakaus/impeccable 5위 · 오늘 +677 / 누적 4,493 makecindy/cindy 6위 · 오늘 +657 / 누적 11,351 pollen-robotics/microduck 7위 · 오늘 +489 / 누적 7,404 Renhuai123/ziwei-doushu 8위 · 오늘 +309 / 누적 113,997 TauricResearch/TradingAgents 화면 자료: 각 프로젝트 공식 저장소의 공개 이미지·데모, Pollen Robotics 공식 Microduck 공개 영상, Impeccable 공식 제작 예시, Cindy 공식 소개 페이지. 공식 자료 발췌이며 MATO가 모든 도구를 설치·실행한 성능 비교 영상은 아닙니다. pollen-robotics.com impeccable.style cindy.app metisziwei.com 아이템 벤치마킹: youtube.com 원본 유튜브 영상의 화면·음성·대사는 사용하지 않았습니다. 대본·편집·음성 합성: MATO. 스타 수는 관심 지표이며 성능이나 투자 수익을 보증하지 않습니다. 프로젝트별 모델·서비스 비용과 이용 조건은 다를 수 있습니다. #깃허브 #오픈소스 #마토 #AI도구 [en-US] The 8 Hottest GitHub Projects Worldwide Revealed Here are 8 projects selected from the GitHub Trending list on October 25, 2026, based on daily star growth. From creating AI voices and refining web designs to controlling robots and checking code security, we examined what each tool does through official screenshots and public demos. Rankings viewed: October 25, 2026, 22:34 (Korea/Japan Time) Scope: Daily / Trending list for all languages. This ranking is not based on a full survey of all GitHub repositories. Today's growth and cumulative stars are separate. ⏱ Timestamps 00:00 Start · TradingAgents 00:37 Zi Wei Dou Shu 01:06 Microduck 01:33 Cindy 02:03 Impeccable 02:31 Hallmark 03:04 VoiceStudio 03:39 Security Audit Skill 04:19 Wrap-up 🔗 GitHub Projects 1st · Today +2,874 / Cumulative 45,953 cloudflare/security-audit-skill 2nd · Today +1,588 / Cumulative 85,833 debpalash/VoiceStudio 3rd · Today +1,359 / Cumulative 32,977 Nutlope/hallmark 4th · Today +1,113 / Cumulative 87,086 pbakaus/impeccable 5th · Today +677 / Cumulative 4,493 makecindy/cindy 6th · Today +657 / Cumulative 11,351 pollen-robotics/microduck 7th · Today +489 / Cumulative 7,404 Renhuai123/ziwei-doushu 8th · Today +309 / Cumulative 113,997 TauricResearch/TradingAgents Screen materials: Public images and demos from each project's official repository, official Pollen Robotics Microduck release video, official Impeccable production example, and official Cindy introduction page. These are excerpts from official materials and are not performance comparison videos where MATO installed and ran all tools. pollen-robotics.com impeccable.style cindy.app metisziwei.com Item benchmarking: youtube.com The screen, audio, and dialogue from the original YouTube video were not used. Script, editing, and voice synthesis: MATO. The number of stars is an indicator of interest and does not guarantee performance or return on investment. Model and service costs and terms of use may vary by project. #GitHub #OpenSource #MATO #AITool

Sorry for the wait, the episode is here! Live action with real robots instead of animation (episode 4): "Anger" Enjoy! As always, the software of Microduck and Reachy Mini is open source: pollen-robotics/microduck pollen-robotics/reachy_mini t.co

今日のGitHubトレンド pollen-robotics/microduck Microduckは強化学習を用いて動作する小型二足歩行ロボットの制御システムです。 本リポジトリはロボットの脳として機能し、RK3566上で動作するコントロールループやサーボ制御、通信、アップデート機能を管理します。 外部で学習されたONNX形式のポリシーを読み込むことで、歩行や物の拾い上げ、転倒からの復帰などの動作を実現します。

A 25 cm, 800 g robot duck learned to walk, tumble, and stand itself back up with reinforcement learning. This repo is the duck's brain — the handful of daemons that actually run it. 11,049 stars, all in Rust. pollen-robotics/microduck t.co

This robot duck has an open-source brain 🦆 #Shorts Microduck runs learned movement policies. Its companion microduck_rl documents MuJoCo-based training and ONNX export for the onboard runtime. Local training requires a CUDA GPU; Hugging Face Jobs is also documented. Software: pollen-robotics/microduck Training: pollen-robotics/microduck_rl Product imagery: pollen-robotics.com Documentary edit of Pollen Robotics' published robot photo/film and native GitHub documentation. No independent robot execution or hardware benchmark performed. Software repo, not a free build kit. Official site lists a $399 introductory pre-order before taxes and shipping, checked 2026-10-25. #Robotics #OpenSource #ReinforcementLearning #Shorts [de-DE] Diese Roboter-Ente hat ein Open-Source-Gehirn 🦆 #Shorts Microduck führt erlernte Bewegungsstrategien aus. Die zugehörige Dokumentation microduck_rl beschreibt das MuJoCo-basierte Training und den ONNX-Export für die Onboard-Laufzeitumgebung. Lokales Training erfordert eine CUDA-GPU; Hugging Face Jobs sind ebenfalls dokumentiert. Software: pollen-robotics/microduck Training: pollen-robotics/microduck_rl Produktbilder: pollen-robotics.com Dokumentarische Bearbeitung der von Pollen Robotics veröffentlichten Roboterfotos/-videos und der zugehörigen GitHub-Dokumentation. Es wurden keine unabhängigen Roboterausführungen oder Hardware-Benchmarks durchgeführt. Software-Repository, kein kostenloses Baukastensystem. Die offizielle Website listet einen Einführungspreis von 399 US-Dollar (vor Steuern und Versand) auf (Stand: 25.10.2026). #Robotik #OpenSource #ReinforcementLearning #Kurzfilme [es-US] Este pato robot tiene un cerebro de código abierto 🦆 #Shorts Microduck ejecuta políticas de movimiento aprendidas. Su documentación complementaria, microduck_rl, describe el entrenamiento basado en MuJoCo y la exportación a ONNX para el entorno de ejecución integrado. El entrenamiento local requiere una GPU CUDA; también se documenta el entrenamiento de Hugging Face. Software: pollen-robotics/microduck Entrenamiento: pollen-robotics/microduck_rl Imágenes del producto: pollen-robotics.com Edición documental de las fotos y vídeos del robot publicados por Pollen Robotics y la documentación nativa de GitHub. No se realizó ninguna ejecución independiente del robot ni pruebas de rendimiento del hardware. Se trata de un repositorio de software, no de un kit de construcción gratuito. El sitio web oficial indica una preventa de lanzamiento por 399 $ (sin impuestos ni gastos de envío), según la información del 25/10/2026. #Robótica #CódigoAbierto #AprendizajePorRefuerzo #Shorts [fr-FR] Ce canard robot a un cerveau open source 🦆 #Shorts Microduck exécute des stratégies de déplacement apprises. Son module complémentaire, microduck_rl, documente l'entraînement basé sur MuJoCo et l'exportation ONNX pour l'environnement d'exécution embarqué. L'entraînement local nécessite un GPU CUDA ; la documentation relative à Hugging Face Jobs est également disponible. Logiciel : pollen-robotics/microduck Entraînement : pollen-robotics/microduck_rl Images du produit : pollen-robotics.com Édition documentaire des photos/vidéos du robot publiées par Pollen Robotics et de la documentation GitHub native. Aucune exécution indépendante du robot ni aucun test de performance matérielle n'ont été effectués. Dépôt logiciel, pas de kit de montage gratuit. Le site officiel affiche un prix de précommande de 399 $ (hors taxes et frais de port), vérifié le 25/10/2026. #Robotique #OpenSource #ApprentissageParRenforcement #CourtesVidéos [hi] इस रोबोट बतख का दिमाग ओपन-सोर्स है 🦆 #Shorts माइक्रोडक सीखी हुई गति नीतियों को संचालित करता है। इसका सहयोगी माइक्रोडक_rl, ऑनबोर्ड रनटाइम के लिए MuJoCo आधारित प्रशिक्षण और ONNX निर्यात का दस्तावेजीकरण करता है। स्थानीय प्रशिक्षण के लिए CUDA GPU की आवश्यकता होती है; हगिंग फेस जॉब्स का भी दस्तावेजीकरण किया गया है। सॉफ्टवेयर: pollen-robotics/microduck प्रशिक्षण: pollen-robotics/microduck_rl उत्पाद चित्र: pollen-robotics.com पॉलेन रोबोटिक्स द्वारा प्रकाशित रोबोट फोटो/फिल्म और मूल GitHub दस्तावेज़ का वृत्तचित्र संपादन। कोई स्वतंत्र रोबोट निष्पादन या हार्डवेयर बेंचमार्क नहीं किया गया है। यह एक सॉफ्टवेयर रिपॉजिटरी है, कोई निःशुल्क बिल्ड किट नहीं। आधिकारिक साइट पर कर और शिपिंग से पहले $399 का परिचयात्मक प्री-ऑर्डर सूचीबद्ध है (2026-10-25 को जाँच की गई)। #रोबोटिक्स #ओपनसोर्स #रीइन्फोर्समेंटलर्निंग #शॉर्ट्स [id] Bebek robot ini punya otak open-source 🦆 #Shorts Microduck menjalankan kebijakan pergerakan yang dipelajari. Pendampingnya, microduck_rl, mendokumentasikan pelatihan berbasis MuJoCo dan ekspor ONNX untuk runtime onboard. Pelatihan lokal membutuhkan GPU CUDA; Hugging Face Jobs juga didokumentasikan. Perangkat Lunak: pollen-robotics/microduck Pelatihan: pollen-robotics/microduck_rl Gambar Produk: pollen-robotics.com Penyuntingan dokumenter dari foto/film robot yang diterbitkan Pollen Robotics dan dokumentasi GitHub asli. Tidak ada eksekusi robot independen atau benchmark perangkat keras yang dilakukan. Repositori perangkat lunak, bukan kit pembuatan gratis. Situs resmi mencantumkan pra-pemesanan pengantar seharga $399 sebelum pajak dan pengiriman, diperiksa pada 25 Oktober 2026. #Robotika #SumberTerbuka #PembelajaranPenguatan #FiturPendek [it] Questa papera robot ha un cervello open source 🦆 #Shorts Microduck esegue politiche di movimento apprese. Il suo complemento microduck_rl documenta l'addestramento basato su MuJoCo e l'esportazione ONNX per il runtime di bordo. L'addestramento locale richiede una GPU CUDA; è documentato anche l'algoritmo Hugging Face Jobs. Software: pollen-robotics/microduck Addestramento: pollen-robotics/microduck_rl Immagini del prodotto: pollen-robotics.com Modifica documentaria delle foto/video del robot pubblicati da Pollen Robotics e della documentazione nativa su GitHub. Non sono state eseguite esecuzioni indipendenti del robot né benchmark hardware. Repository software, non kit di costruzione gratuito. Il sito ufficiale indica un prezzo di preordine introduttivo di $399 tasse e spedizione escluse, verificato il 25/10/2026. #Robotica #OpenSource #ApprendimentoPerRinforzo #Brevi [pt-BR] Este pato robô tem um cérebro de código aberto 🦆 #Shorts O Microduck executa políticas de movimento aprendidas. Seu complemento, o microduck_rl, documenta o treinamento baseado em MuJoCo e a exportação ONNX para o ambiente de execução integrado. O treinamento local requer uma GPU CUDA; o Hugging Face Jobs também está documentado. Software: pollen-robotics/microduck Treinamento: pollen-robotics/microduck_rl Imagens do produto: pollen-robotics.com Edição documental da foto/vídeo do robô publicado pela Pollen Robotics e da documentação nativa do GitHub. Nenhuma execução independente do robô ou benchmark de hardware foi realizada. Repositório de software, não um kit de construção gratuito. O site oficial lista um preço promocional de pré-venda de US$ 399 antes de impostos e frete, verificado em 25/10/2026. #Robótica #CódigoAberto #AprendizadoPorReforço #Curtas

[개발자들의 PICK] 오늘 깃허브 트렌딩 인기 오픈소스 TOP 8 오늘 깃허브 트렌딩에 오른 오픈소스 8개를 8위부터 1위까지 정리했습니다. 소개한 오픈소스 링크는 고정 댓글에 남겨 두었습니다. 00:00 오늘의 깃허브 트렌딩 00:04 8위 제미나이 CLI 00:24 7위 마이크로덕 01:08 6위 임페커블 01:42 5위 클로드 하우투 02:14 4위 홀마크 02:49 3위 AWS 에이전트 툴킷 03:26 2위 엔비디아 오픈셸 04:07 1위 클라우드플레어 시큐리티 오딧 스킬 04:49 마무리 📌 저장소 링크 8위 제미나이 CLI google-gemini/gemini-cli "※ 개인·무료 사용자는 Antigravity CLI로 이전됨: antigravity.google" 7위 마이크로덕 pollen-robotics/microduck 6위 임페커블 pbakaus/impeccable 5위 클로드 하우투 luongnv89/claude-howto 4위 홀마크 Nutlope/hallmark 3위 AWS 에이전트 툴킷 aws/agent-toolkit-for-aws 2위 엔비디아 오픈셸 NVIDIA/OpenShell 1위 클라우드플레어 시큐리티 오딧 스킬 cloudflare/security-audit-skill [en-US] [Developers' PICK] Top 8 Trending Open Source Projects on GitHub Today I have compiled a list of the 8 open source projects that trended on GitHub today, ranking them from 8th to 1st place. I have left the links to the featured open source projects in the pinned comment. 00:00 Today's GitHub Trending 00:04 8th Gemini CLI 00:24 7th Microduck 01:08 6th Impeccable 01:42 5th Claude How-to 02:14 4th Hallmark 02:49 3rd AWS Agent Toolkit 03:26 2nd NVIDIA OpenShell 04:07 1st Cloudflare Security Audit Skills 04:49 Wrap-up 📌 Repository Links 8th Gemini CLI google-gemini/gemini-cli "※ Personal/Free users migrated to Antigravity CLI: antigravity.google" 7th Microduck pollen-robotics/microduck 6th Impeccable pbakaus/impeccable 5th Claude Howto luongnv89/claude-howto 4th Hallmark Nutlope/hallmark 3rd AWS Agent Toolkit aws/agent-toolkit-for-aws 2nd NVIDIA OpenShell NVIDIA/OpenShell 1st Cloudflare Security Audit Skill cloudflare/security-audit-skill [id] [Pilihan Developer] 8 Open Source Paling Trending di GitHub Hari Ini Saya telah menyusun daftar 8 proyek sumber terbuka yang sedang tren di GitHub hari ini, dengan peringkat dari posisi ke-8 hingga ke-1. Saya telah menyertakan tautan ke proyek sumber terbuka unggulan di komentar yang disematkan. 00:00 Tren GitHub Hari Ini 00:04 Gemini CLI ke-8 00:24 Microduck ke-7 01:08 Impeccable ke-6 01:42 Claude How-to ke-5 02:14 Hallmark ke-4 02:49 AWS Agent Toolkit ke-3 03:26 NVIDIA OpenShell ke-2 04:07 Cloudflare Security Audit Skills ke-1 04:49 Ringkasan 📌 Tautan Repositori Gemini CLI ke-8 google-gemini/gemini-cli "※ Pengguna pribadi/gratis dimigrasikan ke Antigravity CLI: antigravity.google" Microduck ke-7 pollen-robotics/microduck Ke-6 Sempurna pbakaus/impeccable Ke-5 Claude Howto luongnv89/claude-howto Ke-4 Hallmark Nutlope/hallmark Ke-3 AWS Agent Toolkit aws/agent-toolkit-for-aws Ke-2 NVIDIA OpenShell NVIDIA/OpenShell Ke-1 Cloudflare Security Audit Skill cloudflare/security-audit-skill

Hugging Face Just Shipped a $399 Robot Duck. Here’s What It Actually Means for NVIDIA. Microduck is not an NVIDIA robot. Per Automate's teardown, it runs on a Rockchip RK3566, and it launched before NVIDIA's $12.9 billion Hugging Face deal was official. But read the training docs and you'll see why NVIDIA is the company that benefits most. !duck The Problem It's Solving Teaching a robot to move is expensive and messy. The robot has to try things, fail, and try again. On a full-size humanoid, Pollen Robotics says, every bad attempt can be costly, hard to reset, or unsafe to run outside a lab. That leaves most developers training legged behaviors purely in simulation, with no cheap way to test whether the policy survives real floors and real motors. Sim-to-real is the hard part of physical AI, and the hardware to practice it has been priced for labs. Microduck is Pollen's answer: a robot small and cheap enough that a failed behavior ends with a duck on the floor, not an incident report. How Microduck Actually Works Microduck is a 25 cm biped under 800 g. It has 15 motors, a camera, a small depth sensor, two IMUs, and an articulated beak that works as a gripper. It walks, sits, crouches, recovers from many common falls, and roller-skates. It can't talk. It makes creature sounds, and each unit gets its own audio identity on first wake. The robot ships with learned behaviors you can trigger with a gamepad, so it's useful before you write any code. Underneath, the whole stack is open. The main repository holds the SDK and robot software. Microduck RL holds the reinforcement learning and sim-to-real tools. Pollen's pitch is that Reachy Mini is a platform for AI that interacts, while Microduck is a platform for AI that acts. The workflow is the standard sim-to-real loop. You train a policy across many simulated ducks, export it, deploy it to the real robot, watch what breaks, and go back to simulation. There is also a browser simulator for running pretrained policies before you own the hardware. !duck2 Here is the NVIDIA part. According to a Chinese-language breakdown of the official training docs, local training needs a CUDA GPU because the pipeline uses MuJoCo Warp. Without one, you can submit the same job to cloud GPUs through Hugging Face Jobs. A community developer ported the training environment to AMD GPUs two days after launch, but that port is unofficial, only partly working, and not yet verified on a real robot. The default path runs on CUDA. What Developers Are Actually Using It For The use cases so far are narrow and technical, which is a good sign. Seeed Studio published a Jetson walkthrough that covers PPO training in MuJoCo on a Jetson Orin NX 16GB, visualizing checkpoints, running the official ONNX policy with keyboard control, and building custom motions. Pollen's own team is pushing the robot's perception. Two October posts cover SLAM with the 8×8 depth sensor and contact odometry from two feet and an IMU, both running fully onboard. Pollen also says Microduck is about ten times more fun in groups, which makes multi-robot experiments (races, football) practical without a room full of expensive hardware. Why This Is a Bigger Deal Than It Looks The sequencing matters. Fortune's report on the NVIDIA talks is dated August 27, the same day Pollen published the Microduck announcement. NVIDIA then confirmed the deal on September 3. Some coverage says Hugging Face turned in Microduck as its first assignment after the acquisition. That's wrong. The robot predates the announcement. Still, the strategic logic holds. Jensen Huang wrote that Hugging Face will stay an open platform and that NVIDIA compute will not be required to build on or deploy through it. Microduck's default training path doesn't contradict that, since the code is open. But a $399 robot whose official pipeline assumes CUDA is a very cheap way to recruit the next generation of robotics developers into NVIDIA's stack. Automate makes the same point: the real opportunity is developer distribution. Robotics is where NVIDIA wants its next platform to be, and Hugging Face brings the community that shares policies the way it already shares models. Pollen frames it the same way: physical behaviors should be as easy to share as models, along with the environments and training recipes to reproduce them. Availability and Access !duck 3 Microduck is open for pre-order at an introductory $399 before taxes and shipping, in Cream, Graphite, Lavender, and Sky. First deliveries are targeted before Christmas 2026 in North America, Europe, and the UK. The software is open under Apache 2.0 and available today. As for the acquisition, reports describe it as expected to close in the first half of 2027, subject to regulatory review. Microduck won't solve robotics, and Pollen says as much. But the company that owns the GPUs, the model hub, and now the cheapest on-ramp to physical AI is assembling a full stack, one duck at a time. Follow for more coverage on MCP, agentic AI, and AI infrastructure.