# opendrivelab/agibot-world

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/opendrivelab-agibot-world).**

2,786 stars · 195 forks · Python

## Links

- GitHub: https://github.com/OpenDriveLab/AgiBot-World
- Homepage: https://opendrivelab.com/AgiBot-World/
- awesome-repositories: https://awesome-repositories.com/repository/opendrivelab-agibot-world.md

## Topics

`pretraining-for-robotics` `robotic-foundation-model` `robotic-manipulation` `vision-language-action-model`

## Description

AgiBot-World is a suite of software pipelines and tools designed for robotic policy training, dataset standardization, embodiment transfer, and performance benchmarking. It provides infrastructure for developing bimanual manipulation policies using foundation models and human-reference trajectory data.

The project features a robot embodiment transfer suite that adapts pre-trained models to different robot bodies without requiring new multi-embodiment training data. It also includes a specialized evaluation framework for validating vision-language-action models through open-loop testing and physical hardware replays.

The system covers a broad range of capabilities including robotic manipulation benchmarking, the conversion of raw datasets into standardized layouts, and the fine-tuning of physical AI and autonomous driving models. It further supports model inference execution via local controllers or remote servers and the development of modular, dexterous hardware for multimodal grasping.

## Tags

### Artificial Intelligence & ML

- [Bimanual Manipulation Training](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/robot-policy-trainers/bimanual-manipulation-training.md) — Develops robotic models for complex bimanual manipulation using foundation models and large trajectory datasets.
- [Embodiment Adaptations](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/robot-policy-trainers/embodiment-adaptations.md) — Implements a suite for adapting pre-trained models to different robot bodies without requiring new multi-embodiment training data.
- [Cross-Embodiment Transfer](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-embodiment-transfer.md) — Features a suite that adapts pre-trained models to different robot bodies without requiring new multi-embodiment training data.
- [Robotic Trajectory Standardizers](https://awesome-repositories.com/f/artificial-intelligence-ml/dataset-management/evaluation-datasets/evaluation-dataset-standardizers/robotic-trajectory-standardizers.md) — Ships utilities to transform raw robotic data from various formats into standardized layouts for training. ([source](https://cdn.jsdelivr.net/gh/opendrivelab/agibot-world@main/README.md))
- [Demonstration Tracking](https://awesome-repositories.com/f/artificial-intelligence-ml/human-in-the-loop-systems/demonstration-tracking.md) — Implements training loops that utilize human-reference trajectory data to guide the learning of complex physical tasks.
- [VLA Model Validation](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-frameworks/vision-model-training/vision-language-action-training/vla-model-validation.md) — Provides a framework for validating vision-language-action models through open-loop testing and physical hardware replays.
- [Robotic Policy Evaluators](https://awesome-repositories.com/f/artificial-intelligence-ml/performance-evaluation-tools/robotic-policy-evaluators.md) — Implements a platform for measuring accuracy and generalization in robotic manipulation tasks using large scale datasets. ([source](https://opendrivelab.com/))
- [Open-Loop Evaluations](https://awesome-repositories.com/f/artificial-intelligence-ml/performance-evaluation-tools/robotic-policy-evaluators/open-loop-evaluations.md) — Includes a pipeline to replay recorded actions and measure policy accuracy before real-world hardware execution.
- [Physical AI Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/physical-ai-fine-tuning.md) — Refines autonomous driving and manipulation models using real-world data and production-validated infrastructure.
- [Trajectory Standardization](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training-pipelines/multi-modal-training/trajectory-standardization.md) — Implements a unified data format that normalizes diverse robotic sensor streams and actions for consistent training.
- [Scalable Robot Policy Trainings](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/robot-policy-trainers/scalable-robot-policy-trainings.md) — Provides a comprehensive infrastructure for developing bimanual manipulation policies using foundation models and human-reference data.
- [Bimanual Manipulation Trainings](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/robot-policy-trainers/scalable-robot-policy-trainings/bimanual-manipulation-trainings.md) — Develops bimanual manipulation policies using large-scale trajectory datasets and pre-trained foundation models. ([source](https://cdn.jsdelivr.net/gh/opendrivelab/agibot-world@main/README.md))
- [Robotic Arm Training](https://awesome-repositories.com/f/artificial-intelligence-ml/reinforcement-learning-training/robot-policy-trainers/scalable-robot-policy-trainings/robotic-arm-training.md) — Uses human references and adaptive tracking to enable robotic arms to perform complex physical manipulation tasks. ([source](https://opendrivelab.com/))
- [Custom Data Fine-Tunings](https://awesome-repositories.com/f/artificial-intelligence-ml/full-parameter-fine-tuning/custom-data-fine-tunings.md) — Adapts pre-trained robotic policies to specific tasks or new environments using custom user-provided datasets. ([source](https://cdn.jsdelivr.net/gh/opendrivelab/agibot-world@main/README.md))
- [Standardized Evaluation Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/reinforcement-learning-environments/reinforcement-learning-performance-visualizers/agent-performance-evaluators/standardized-evaluation-protocols.md) — Defines a protocol for controlling environmental noise and lighting to ensure reproducible robot testing results. ([source](https://opendrivelab.com/OpenGO1/))
- [Inference Execution Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/engines-runtimes-servers/inference-execution-models.md) — Executes trained policies via local controllers or remote servers to translate sensor observations into robotic actions. ([source](https://cdn.jsdelivr.net/gh/opendrivelab/agibot-world@main/README.md))
- [Adversarial Robustness Training](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/adversarial-training-procedures/adversarial-robustness-training.md) — Provides methods for introducing synthetic noise and environmental shifts to improve model robustness during training.
- [Training Data Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/training-data-generation.md) — Provides processes for introducing environmental changes and task shifts to increase training data efficiency. ([source](https://opendrivelab.com/OpenGO1/))

### Part of an Awesome List

- [VLA](https://awesome-repositories.com/f/awesome-lists/ai/model-validation/vla.md) — Provides a testing suite for vision-language-action models using open-loop validation and hardware replays. ([source](https://opendrivelab.com/OpenGO1/))
- [Autonomous Driving Refinements](https://awesome-repositories.com/f/awesome-lists/ai/model-training-and-fine-tuning/model-fine-tuning/autonomous-driving-refinements.md) — Provides a production-validated environment for fine-tuning autonomous driving models using real-world data. ([source](https://opendrivelab.com/))

### Hardware & IoT

- [Robot Learning Platforms](https://awesome-repositories.com/f/hardware-iot/embedded-robotics/robotics-autonomous-systems/robotics-drones/robotic-tooling/robot-learning-platforms.md) — Offers a platform for measuring accuracy and generalization in robot manipulation tasks using large-scale trajectory datasets.
- [Modular Physical Architectures](https://awesome-repositories.com/f/hardware-iot/custom-robot-hardware-design/modular-physical-architectures.md) — Ships a lightweight physical architecture with interchangeable components for multimodal grasping and various body configurations.
- [Dexterous Robot Hand Design](https://awesome-repositories.com/f/hardware-iot/dexterous-robot-hand-design.md) — Provides a modular, lightweight hardware design enabling multimodal robotic grasping and manipulation. ([source](https://opendrivelab.com/))
- [Robotics Visualization Tools](https://awesome-repositories.com/f/hardware-iot/integration-performance/hardware-interfacing-integration/hardware-integration/device-sensors/remote-sensor-queries/sensor-data-visualizers/robotics-visualization-tools.md) — Provides tools for rendering camera streams, robot states, and actions from trajectory datasets to inspect data quality. ([source](https://cdn.jsdelivr.net/gh/opendrivelab/agibot-world@main/README.md))
- [Policy Servers](https://awesome-repositories.com/f/hardware-iot/robot-action-streaming-servers/policy-servers.md) — Provides a decoupled execution model that hosts policies on GPU servers and streams actions to local controllers.

### System Administration & Monitoring

- [Execution Fidelity Validation](https://awesome-repositories.com/f/system-administration-monitoring/execution-history-auditors/reverse-execution-simulation/record-and-replay-debugging/data-stream-recording-and-replay/robotics-data-recording/execution-fidelity-validation.md) — Provides a method for replaying recorded demonstrations on hardware to measure execution fidelity against original recordings. ([source](https://opendrivelab.com/OpenGO1/))