README.md

---
title: README
emoji: 📊
colorFrom: indigo
colorTo: blue
sdk: streamlit
pinned: false
---

<img src="assets/agibot_world.png" alt="Image Alt Text" width="70%" style="display: block; margin-left: auto; margin-right: auto;" />


Most existing robot learning benchmarks struggle with real-world challenges due to low-quality data and limited sensing capabilities, often constrained to short-horizon tasks in controlled environments.
Introducing AgiBot World, the first large-scale robotic learning dataset and benchmark designed to advance multi-purpose robotic manipulation. It integrates data, models, benchmarks, and an ecosystem to democratize access to real-robot data for the academic community, paving the way for an "ImageNet moment" in Embodied AI.
With 1M+ high-fidelity demonstrations from 100 robots, Agibot spans 100+ real-world scenarios across five business sectors, tackling fine-grained manipulation, tool usage, and dual-robot collaboration. Cutting-edge multimodal hardware features visual tactile sensors, durable 6-DoF dexterous hands, and mobile dual-arm robots with full-body control, supporting research in imitation learning, multi-agent collaboration, and more.
AgiBot World aspires to transform large-scale robot learning and advance scalable robotic systems for production. This open-source platform invites researchers and practitioners to collaboratively shape the future of Embodied AI.