Skip to content
Back to search

physical-ai-studio

Physical AI Studio is an end-to-end framework for training robots to perform tasks through imitation learning from human demonstrations.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/open-edge-platform/physical-ai-studio with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/open-edge-platform/physical-ai-studio'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/open-edge-platform--physical-ai-studio/badge.svg)](/listings/open-edge-platform--physical-ai-studio)

HTML

<a href="/listings/open-edge-platform--physical-ai-studio"><img src="/api/listings/open-edge-platform--physical-ai-studio/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Application (GUI)

For users who prefer a visual interface for end-to-end workflow:

<p align="center"> <a href="docs/assets/physical_ai_studio_full_overview.mp4"> </a> </p>

[Download the full demo video →](docs/assets/physical_ai_studio_full_overview.mp4)

[Application Documentation →](./application/README.md)

Docker

Run the full application (backend + UI) in a single container (using [Docker](https://docs.docker.com/engine/install/ubuntu/)):

# Clone the repository
git clone https://github.com/open-edge-platform/physical-ai-studio.git
cd physical-ai-studio

# Setup and run docker services
cd application/docker
./setup-devices.sh --xpu # or use --cuda, --cpu
docker compose up -d

Application runs at <http://localhost:7860>. See the [Docker README](./application/docker/README.md) for hardware configuration (Intel XPU, NVIDIA CUDA) and device setup.

If you plan to train Hugging Face Hub-backed policies (for example, SmolVLA, Pi0.5, and others), configure `HF_TOKEN` to avoid unauthenticated Hub access warnings. See [Hugging Face Integration](./application/backend/docs/huggingface_integration.md).

Native: installation & running

Run the application in development mode, using [uv package manager](https://docs.astral.sh/uv/getting-started/installation/) and [node v24](https://nodejs.org/en/download) (we recommend using nvm)

Note: native setup requires additional OS-level libraries (OpenCV/video/USB and Python build dependencies). See the **Prerequisites** section in [Application Installation](./application/docs/01-installation.md#prerequisites).

# Clone the repository
git clone https://github.com/open-edge-platform/physical-ai-studio.git
cd physical-ai-studio

# Install and run backend
cd application/backend

# Start the backend, or use --extra cpu, --extra cuda
uv run --extra xpu physicalai-studio serve  # or: ./run.sh
# In a new terminal: install and run UI
cd application/ui
npm install

# Start the UI
npm run start

Open <http://localhost:3000> in your browser.

If you plan to train Hugging Face Hub-backed policies (for example, SmolVLA, Pi0.5, and others), configure a Hugging Face token in Settings > General > Hugging Face in the UI to avoid unauthenticated Hub access warnings. See [Hugging Face Integration](./application/backend/docs/huggingface_integration.md).

Library (Python/CLI)

For programmatic control over training, benchmarking, and deployment with both API and CLI

pip install physicalai-train

<details open> <summary>Training</summary>

from physicalai.data import LeRobotDataModule
from physicalai.policies import ACT
from physicalai.train import Trainer

datamodule = LeRobotDataModule(repo_id="lerobot/aloha_sim_transfer_cube_human")
model = ACT()
trainer = Trainer(max_epochs=100)
trainer.fit(model=model, datamodule=datamodule)

</details>

<details> <summary>Benchmark</summary>

from physicalai.benchmark import LiberoBenchmark
from physicalai.policies import ACT

policy = ACT.load_from_checkpoint("experiments/lightning_logs/version_0/checkpoints/last.ckpt")
benchmark = LiberoBenchmark(task_suite="libero_10", num_episodes=20)
results = benchmark.evaluate(policy)
print(f"Success rate: {results.aggregate_success_rate:.1f}%")

</details>

<details> <summary>Export</summary>

from physicalai.export import get_available_backends
from physicalai.policies import ACT

# See available backends
print(get_available_backends())  # ['onnx', 'openvino', 'torch', 'executorch']

# Export to OpenVINO
policy = ACT.load_from_checkpoint("experiments/lightning_logs/version_0/checkpoints/last.ckpt")
policy.export("./policy", backend="openvino")

</details>

<details> <summary>Inference</summary>

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 170 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <img src="docs/assets/physical_ai_studio.png" alt="Physical AI Studio" width="100%">
  3. </p>
  4. <div align="center">
  5. **Physical AI Studio helps teams train, benchmark, and deploy robot policies from demonstrations.**
  6. [Studio UI](#studio-ui) • [Python API](#python-api) • [CLI](#cli) • [Policies](#policies) • [Install](#install) • [Documentation](#documentation)
  7. </div>
  8. ---
  9. ## Studio UI
  10. Collect demonstrations, train policies, and run inference through a visual interface.
  11. <!-- markdownlint-disable MD033 -->
  12. <p align="center">
  13. <img src="docs/assets/readme/gui-demo.gif" alt="Physical AI Studio UI demo: configure robots and cameras, record data, train, review models, and deploy to robots" width="100%">
  14. </p>
  15. <!-- markdownlint-enable MD033 -->
  16. [Start Studio with Docker](./application/docs/01-installation.md#install-with-docker-recommended) · [Native setup](./application/docs/01-installation.md#alternatively-install-natively)
  17. <details>
  18. <summary>Copy Docker start commands</summary>
  19. ```bash
  20. git clone https://github.com/open-edge-platform/physical-ai-studio.git
  21. cd physical-ai-studio/application/docker
  22. cp .env.example .env
  23. ./setup-devices.sh --cpu # or --xpu or --cuda
  24. docker compose up -d
  25. ```
  26. Open <http://localhost:7860>. See the [Docker guide](./application/docker/README.md) for hardware options and setup. Configure `HF_TOKEN` in `application/docker/.env` for Hugging Face-backed policies; see [Hugging Face integration](./application/backend/docs/huggingface_integration.md).
  27. </details>
  28. <details>
  29. <summary>Native development commands</summary>
  30. Native setup is for contributors and requires OS-level libraries, [uv](https://docs.astral.sh/uv/getting-started/installation/), and [Node.js v24](https://nodejs.org/en/download). See the [prerequisites](./application/docs/01-installation.md#prerequisites).
  31. In one terminal, from the repository root:
  32. ```bash
  33. cd application/backend
  34. uv run --extra xpu physicalai-studio serve # or --extra cpu / --extra cuda
  35. ```
  36. In a second terminal, also from the repository root:
  37. ```bash
  38. cd application/ui
  39. npm install
  40. npm run start
  41. ```
  42. Open <http://localhost:3000>. For native Hugging Face setup, use **Settings > General > Hugging Face**.
  43. </details>
  44. ## Python API
  45. Train, benchmark, and export policies programmatically.
  46. <!-- markdownlint-disable MD033 -->
  47. <p align="center">
  48. <img src="docs/assets/readme/api-demo.gif" alt="Python API demo: train, benchmark, export, and deploy a policy" width="100%">
  49. </p>
  50. <!-- markdownlint-enable MD033 -->
  51. The library also supports LIBERO and RoboCasa benchmarks; see the [benchmarking guide](./library/docs/getting-started/first-benchmark.md) for suite-specific setup and checkpoint requirements.
  52. <details>
  53. <summary>Copy the Python example</summary>
  54. ```python test="skip" reason="requires dataset download and robot observation"
  55. from physicalai.benchmark.gyms import PushTBenchmark
  56. from physicalai.data import LeRobotDataModule
  57. from physicalai.inference import InferenceModel
  58. from physicalai.policies import ACT
  59. from physicalai.train import Trainer
  60. datamodule = LeRobotDataModule(repo_id="lerobot/pusht", num_workers=0)
  61. policy = ACT()
  62. trainer = Trainer(max_epochs=100)
  63. trainer.fit(model=policy, datamodule=datamodule)
  64. benchmark = PushTBenchmark(num_episodes=50)
  65. results = benchmark.evaluate(policy)
  66. policy.export("./exports/act", backend="openvino")
  67. runtime_policy = InferenceModel("./exports/act")
  68. ```
  69. </details>
  70. A PushT-trained policy is not directly usable on a physical robot; use a policy trained for that robot with a matching Runtime config. See the [robot deployment guide](https://github.com/openvinotoolkit/physicalai/blob/main/docs/getting-started/run-a-policy.md).
  71. ## CLI
  72. Run Studio training, benchmarking, and export from Runtime's `physicalai` CLI; Runtime also provides the `run` command for deployment.
  73. <details>
  74. <summary>Copy the CLI commands</summary>
  75. The example configs live in `library/configs`; run these Studio commands from `library/` in a cloned repository:
  76. ```bash
  77. # From the repository root
  78. cd library
  79. # Train on PushT
  80. physicalai fit \
  81. --config configs/physicalai/act/pusht/default.yaml
  82. # Benchmark the trained checkpoint
  83. physicalai benchmark \
  84. --config configs/benchmark/pusht.yaml \
  85. --policy physicalai.policies.ACT \
  86. --ckpt_path experiments/lightning_logs/version_0/checkpoints/last.ckpt
  87. # Export for deployment
  88. physicalai export \
  89. --policy physicalai.policies.ACT \
  90. --ckpt_path experiments/lightning_logs/version_0/checkpoints/last.ckpt \
  91. --backend openvino \
  92. --output_dir exports/act
  93. ```
  94. From your Runtime project, run a robot policy with:
  95. ```bash
  96. physicalai run --config runtime.yaml
  97. ```
  98. Use the [Runtime config example](https://github.com/openvinotoolkit/physicalai/blob/main/docs/how-to/config/write-runtime-config.md) as `runtime.yaml`; it is separate from the PushT training config above.
  99. </details>
  100. ## Policies
  101. Native policy families include ACT, Pi0.5, SmolVLA, MolmoAct2, RLDX-1, XR0, and Cosmos3; see the library’s [supported policies](./library/README.md#supported-policies).
  102. ## Install
  103. Use the library for Python API and CLI workflows, or follow the Studio UI setup above. The library supports Python 3.12–3.14.
  104. See the [library installation guide](./library/docs/getting-started/installation.md) for source installs and optional dependencies.
  105. <details>
  106. <summary>Copy the Python install command</summary>
  107. ```bash
  108. pip install physicalai-train
  109. ```
  110. For hardware-specific PyTorch packages, use the source installation instructions
  111. in the [library installation guide](./library/docs/getting-started/installation.md).
  112. </details>
  113. ## Documentation
  114. [Library](./library/README.md) · [Application](./application/README.md) · [Contributing](./CONTRIBUTING.md)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.