# phospho ## Docs - [Start the auto control by AI](https://docs.phospho.ai/ai-training/ai-control-start.md): Start the auto control by AI. - [Stop the auto control by AI](https://docs.phospho.ai/ai-training/ai-control-stop.md): Stop the auto control by AI. - [Cancel Training](https://docs.phospho.ai/ai-training/cancel-training.md): Cancel a training job - [Start training a model](https://docs.phospho.ai/ai-training/start-training.md): Start training an ACT or gr00t model on the specified dataset. This will upload a trained model to the Hugging Face Hub using the main branch of the specified dataset. - [Manipulate LeRobot datasets](https://docs.phospho.ai/basic-usage/dataset-operations.md): How to repair, merge, split and delete LeRobot datasets - [Record a robotics dataset](https://docs.phospho.ai/basic-usage/dataset-recording.md): How to record a robotics dataset with your robot? - [Control robot with AI models](https://docs.phospho.ai/basic-usage/inference.md): How to make an AI model control your robot? - [Control your robot arm](https://docs.phospho.ai/basic-usage/teleop.md): How to remote control a robot arm with a keyboard, in VR, with an API or a leader arm? - [Train a robotics AI model](https://docs.phospho.ai/basic-usage/training.md): How to train a robotics AI model with a dataset? - [Refresh Camera List](https://docs.phospho.ai/camera/cameras-refresh.md): Refresh the list of available cameras. This operation can take a few seconds as it disconnects and reconnects to all cameras. It is useful when cameras are added or removed while the application is running. - [Get All Camera Frames](https://docs.phospho.ai/camera/frames.md): Capture frames from all available cameras. Returns a dictionary with camera IDs as keys and base64 encoded JPG images as values. If a camera is not available or fails to capture, its value will be None. - [Video Feed For Camera](https://docs.phospho.ai/camera/video-feed-for-camera.md): Stream video feed of the specified camera. If no camera id is provided, the default camera is used. Specify a target size and quality using query parameters. - [Calibrate Robot](https://docs.phospho.ai/control/calibration-sequence.md): Start the calibration sequence for the robot. - [Read End-Effector Position](https://docs.phospho.ai/control/end-effector-state.md): Retrieve the position, orientation, and open status of the robot's end effector. Only available for manipulators. - [Move to Absolute Position](https://docs.phospho.ai/control/move-absolute-position.md): Move the robot to an absolute position specified by the end-effector (in centimeters and degrees). Make sure to call `/move/init` before using this endpoint. - [Initialize Robot](https://docs.phospho.ai/control/move-init.md): Initialize the robot to its initial position before starting the teleoperation. - [Use the leader arm to control the follower arm](https://docs.phospho.ai/control/move-leader-start.md): Use the leader arm to control the follower arm. - [Stop the leader-follower control](https://docs.phospho.ai/control/move-leader-stop.md): Stop the leader-follower control. - [Move to Relative Position](https://docs.phospho.ai/control/move-relative-position.md): Move the robot to a relative position based on received delta values (in centimeters and degrees). - [Teleoperation Control](https://docs.phospho.ai/control/move-teleoperation.md) - [Teleoperation Control (WebSocket)](https://docs.phospho.ai/control/move-teleoperation-ws.md): High frequency control of the robot arm via WebSocket connection for real-time updates and commands. - [Read Joint Positions](https://docs.phospho.ai/control/read-joints.md): Read the current positions of the robot's joints in radians and motor units. - [Read Temperature](https://docs.phospho.ai/control/read-temperature.md): Read the current Temperature and maximum Temperature of the robot's motors. - [Read Torque](https://docs.phospho.ai/control/read-torques.md): Read the current torque of the robot's joints. - [Toggle Torque](https://docs.phospho.ai/control/turn-torque.md): Enable or disable the torque of the robot. - [Write Joint Positions](https://docs.phospho.ai/control/write-joints.md): Move the robot's joints to the specified angles. - [Write the Maximum Temperature for Joints](https://docs.phospho.ai/control/write-temperature.md): Set the robot's maximum temperature for motors.. - [Simple controls](https://docs.phospho.ai/examples/control.md): How to control the robot arm with API calls. - [MCP Robotics: Controlling Robots with LLMs using phosphobot MCP](https://docs.phospho.ai/examples/mcp-for-robotics.md): Connect a Large Language Model to a robot using the Model Context Protocol (MCP) and phosphobot. - [VR Control with a Meta Quest](https://docs.phospho.ai/examples/teleop.md): How to control your robot arm using a Meta Quest 2, Pro, 3, 3s over a local WiFi network - [VR Control from anywhere in the world](https://docs.phospho.ai/examples/teleop-from-anywhere.md): How to control your robot arm from anywhere in the world using ngrok and a Meta Quest 2, Pro, 3 or 3s - [Computer vision](https://docs.phospho.ai/examples/vision.md): How to leverage vision models for robotics. - [Frequently Asked Questions](https://docs.phospho.ai/faq.md): Answers to common questions about phosphobot - [Install phosphobot](https://docs.phospho.ai/installation.md): Control your robot arm in seconds with phosphobot on any computer - [Train robotics AI models](https://docs.phospho.ai/learn/ai-models.md): A guide to training AI models that control robots - [Cameras](https://docs.phospho.ai/learn/cameras.md): What are the different cameras used for robotics ? - [Gravity Compensation](https://docs.phospho.ai/learn/gravity-compensation.md): Understanding Gravity Compensation in Robotics - [How to train a good AI model](https://docs.phospho.ai/learn/improve-robotics-ai-model.md): Best practices for recording a dataset for imitation learning in robotics - [Kinematics](https://docs.phospho.ai/learn/kinematics.md): How to move a robot arm to a specific position. - [LeRobot Dataset Format](https://docs.phospho.ai/learn/lerobot-dataset.md): Learn about the LeRobot dataset format: its structure, versions, how to use it, and common tips. - [Core Robotics Concepts](https://docs.phospho.ai/learn/overview.md): The basics to get started in robotics. - [Policies in AI Robotics](https://docs.phospho.ai/learn/policies.md): What are the latest AI robotics models? - [Train SmolVLA](https://docs.phospho.ai/learn/train-smolvla.md): How to Train and Run SmolVLA with LeRobot: A Step-by-Step Guide - [Play Recording](https://docs.phospho.ai/recording/play-recording.md): Play a recorded episode. - [Start Recording Episode](https://docs.phospho.ai/recording/start-recording-episode.md): Asynchronously start recording an episode in the background. Output format is chosen when stopping the recording. - [Stop Recording Episode](https://docs.phospho.ai/recording/stop-recording-episode.md): Stop the recording of the episode. The data is saved to disk to the user home directory, in the `phosphobot` folder. - [SO-100 quickstart guide](https://docs.phospho.ai/so-100/quickstart.md): How to set up phosphobot and control your SO-100 robot arm - [SO-101 Quickstart Guide](https://docs.phospho.ai/so-101/quickstart.md): How to set up phosphobot and control your SO-101 robot arms - [Dev kit unboxing (DK1)](https://docs.phospho.ai/unboxings/dk1.md): Unbox and set up your phospho dev kit. - [Starter pack unboxing (DK2)](https://docs.phospho.ai/unboxings/dk2.md): Unbox and set up your phospho starter pack. - [Welcome to phosphobot](https://docs.phospho.ai/welcome.md): An absurdly simple way to train AI models for real-world robots, built for ML engineers. ## OpenAPI Specs - [openapi](https://docs.phospho.ai/openapi.yml) - [package](https://docs.phospho.ai/package.json) ## Optional - [phospho pro](https://phospho.ai/pro?utm_source=docs) - [Github](https://github.com/phospho-app/phosphobot)