Telekinesis Skill Examples

Free TierEvery new account starts on a free tier with credits to call the SDK — no billing details required.Create API key →

Prerequisites

New here? Complete the Quickstart first — it sets up your API key, conda environment, and SDK in under 5 minutes.

Run an Example!

Run any example from telekinesis-examples repository

Clone the repository and the `telekinesis-data` submodule

bash

git clone --depth 1 --recurse-submodules --shallow-submodules \
  https://github.com/telekinesis-ai/telekinesis-examples.git

cd telekinesis-examples

What gets downloaded?

The flags above keep the clone small:

--depth 1 fetches only the latest commit, not full history.
--recurse-submodules --shallow-submodules also pulls the telekinesis-data submodule (sample images, point clouds, robot states), again at depth 1. Roughly 1.5 GB of free disk space is required for the telekinesis-data.

When you start using Telekinesis on your own data, you can ignore the telekinesis-data submodule - it exists purely to make the examples runnable out of the box.

Install dependencies for examples

bash

conda activate telekinesis
pip install rerun-sdk==0.31.2 pycocotools scipy

Run an example (see more examples below)

Runs segment_image_using_sam and visualizes masks in Rerun.

bash

python examples/cornea_examples.py --example segment_image_using_sam

SAM segmentation example: input image on the left, segmentation masks on the right

SAM masks predicted from the sample input image.

Cornea

List all available examples and run one:

bash

python examples/cornea_examples.py --list

bash

python examples/cornea_examples.py --example <name>

Example name	What it covers
`segment_image_using_rgb`	Segments regions by thresholding raw RGB color channels.
`segment_image_using_hsv`	Segments regions by thresholding hue, saturation, and value.
`segment_image_using_lab`	Segments regions using perceptually uniform LAB color space.
`segment_image_using_ycrcb`	Segments regions by separating luminance from chroma components.
`segment_image_using_focus_region`	Isolates a rectangular region of interest for downstream processing.
`segment_image_using_watershed`	Segments touching or overlapping objects using the watershed algorithm.
`segment_image_using_flood_fill`	Segments a contiguous region by flood-filling from a seed point.
`segment_image_using_foreground_birefnet`	Extracts foreground from background using the BiRefNet deep learning model.
`segment_image_using_sam`	Segments arbitrary objects using Meta's Segment Anything Model (SAM).
`segment_image_using_grab_cut`	Separates foreground from background using the GrabCut graph-cut algorithm.
`segment_image_using_felzenszwalb`	Over-segments an image into superpixels using Felzenszwalb's method.
`segment_image_using_slic_superpixel`	Groups pixels into compact superpixels using the SLIC algorithm.
`filter_segments_by_area`	Removes segments outside a specified minimum or maximum area.
`filter_segments_by_color`	Keeps only segments whose average color falls within a target range.
`filter_segments_by_mask`	Filters segments based on overlap with a provided binary mask.
`segment_image_using_otsu_threshold`	Binarizes an image by automatically finding the optimal Otsu threshold.
`segment_image_using_local_threshold`	Applies adaptive thresholding over local image neighborhoods.
`segment_image_using_yen_threshold`	Binarizes an image using Yen's maximum correlation thresholding method.
`segment_image_using_threshold`	Segments an image using a fixed manually specified threshold value.
`segment_image_using_adaptive_threshold`	Computes per-pixel thresholds based on local mean or Gaussian-weighted neighborhood.
`segment_image_using_laplacian_threshold`	Detects and segments edges by thresholding the Laplacian of the image.

bash

python examples/cornea_examples.py --example segment_image_using_rgb

Retina

List all available examples and run one:

bash

python examples/retina_examples.py --list

bash

python examples/retina_examples.py --example <name>

Example name	What it covers
`detect_circle_using_classic_hough`	Detects circles in an image using the classical Hough Circle Transform.
`detect_contours`	Finds and draws object contours using edge-based detection.
`detect_objects_using_yolox`	Detects objects using the YOLOX neural network model.
`detect_objects_using_rfdetr`	Detects objects using the RF-DETR transformer-based detection model.
`detect_objects_using_qwen`	Detects and describes objects using the Qwen vision-language model.
`detect_objects_using_grounding_dino`	Detects objects from free-text prompts using Grounding DINO.

bash

python examples/retina_examples.py --example detect_contours

Pupil

List all available examples and run one:

bash

python examples/pupil_examples.py --list

bash

python examples/pupil_examples.py --example <name>

Example name	What it covers
`filter_image_using_morphological_erode`	Shrinks bright regions by eroding pixel boundaries.
`filter_image_using_morphological_dilate`	Expands bright regions by dilating pixel boundaries.
`filter_image_using_morphological_close`	Fills small holes and gaps by closing morphological regions.
`filter_image_using_morphological_open`	Removes small noise while preserving larger structures.
`filter_image_using_morphological_gradient`	Highlights edges by computing the morphological gradient.
`filter_image_using_morphological_tophat`	Extracts small bright features against a dark background.
`filter_image_using_morphological_blackhat`	Extracts small dark features against a bright background.
`filter_image_using_morphological_hitmiss`	Detects specific pixel patterns using hit-or-miss morphology.
`filter_image_using_frangi`	Enhances tubular and vessel-like structures using the Frangi filter.
`filter_image_using_hessian`	Highlights blob and ridge structures using Hessian-based filtering.
`filter_image_using_sato`	Detects tubular structures using the Sato vesselness filter.
`filter_image_using_meijering`	Enhances neurite-like ridges using the Meijering filter.
`filter_image_using_laplacian`	Sharpens edges by applying the Laplacian second-derivative filter.
`filter_image_using_sobel`	Detects edges by computing the Sobel gradient magnitude.
`filter_image_using_scharr`	Detects edges with improved rotational accuracy using the Scharr operator.
`filter_image_using_gabor`	Extracts texture features at specific orientations and frequencies using a Gabor filter.
`filter_image_using_bilateral`	Smooths an image while preserving sharp edges using bilateral filtering.
`filter_image_using_box`	Applies a uniform box blur to smooth the image.
`filter_image_using_gaussian_blur`	Smooths an image using a Gaussian kernel to reduce noise.
`filter_image_using_median_blur`	Removes salt-and-pepper noise using median filtering.
`filter_image_using_blur`	Applies a simple average blur to the image.
`enhance_image_using_auto_gamma_correction`	Automatically adjusts image brightness using gamma correction.
`enhance_image_using_white_balance`	Corrects color casts by adjusting white balance.
`enhance_image_using_clahe`	Improves local contrast using Contrast Limited Adaptive Histogram Equalization.
`transform_image_using_pyramid_downsampling`	Reduces image resolution using Gaussian pyramid downsampling.
`transform_image_using_pyramid_upsampling`	Increases image resolution using Laplacian pyramid upsampling.
`transform_mask_using_blob_thinning`	Skeletonizes binary mask blobs to single-pixel-wide lines.
`calculate_image_pca`	Computes principal components of pixel data for dimensionality analysis.
`calculate_image_centroid`	Calculates the centroid of intensity or binary regions in an image.
`convert_image_color_space`	Converts an image between color spaces (e.g. BGR to HSV).
`normalize_image_intensity`	Rescales pixel intensities to a standard range.
`split_image_into_channels`	Splits a multi-channel image into individual channel images.
`merge_image_from_channels`	Merges separate channel images into a single multi-channel image.
`resize_image`	Resizes an image to a specified width and height.
`resize_image_with_aspect_fit`	Resizes an image while preserving its aspect ratio.
`rotate_image`	Rotates an image by a given angle around its center.
`translate_image`	Shifts an image by a specified pixel offset.
`pad_image`	Adds padding around the image borders.
`crop_image_center`	Crops a region from the center of an image.
`crop_image_using_bounding_boxes`	Crops regions from an image using bounding box coordinates.
`crop_image_using_polygon`	Crops and masks a region defined by a polygon.
`bitwise_and_images`	Combines two images using a bitwise AND operation.
`bitwise_or_images`	Combines two images using a bitwise OR operation.
`bitwise_xor_images`	Highlights differences between two images using bitwise XOR.
`bitwise_difference_images`	Computes the absolute pixel difference between two images.
`bitwise_not_image`	Inverts pixel values using a bitwise NOT operation.
`overlay_images_using_weighted_overlay`	Blends two images together using configurable weights.
`project_pixel_to_camera_point`	Back-projects a 2D pixel to a 3D camera-frame point using depth.
`project_camera_point_to_pixel`	Projects a 3D camera-frame point onto the 2D image plane.
`project_pixel_to_world_point`	Back-projects a 2D pixel to a 3D world-frame point using depth and pose.
`project_world_point_to_pixel`	Projects a 3D world-frame point onto the 2D image plane.

bash

python examples/pupil_examples.py --example filter_image_using_sobel

Vitreous

List all available examples and run one:

bash

python examples/vitreous_examples.py --list

bash

python examples/vitreous_examples.py --example <name>

Example name	What it covers
`calculate_axis_aligned_bounding_box`	Computes the axis-aligned bounding box of a point cloud.
`calculate_oriented_bounding_box`	Computes the tightest oriented bounding box around a point cloud.
`calculate_point_cloud_centroid`	Calculates the geometric centroid of a point cloud.
`calculate_points_in_point_cloud`	Returns the total number of points in a point cloud.
`calculate_plane_normal`	Estimates the normal vector of a planar surface in a point cloud.
`cluster_point_cloud_using_dbscan`	Groups points into clusters using the DBSCAN density-based algorithm.
`cluster_point_cloud_based_on_density_jump`	Segments clusters by detecting jumps in local point density.
`convert_mesh_to_point_cloud`	Samples a point cloud from the surface of a 3D mesh.
`create_cylinder_mesh`	Creates a parametric cylinder mesh.
`create_plane_mesh`	Creates a parametric plane mesh.
`create_sphere_mesh`	Creates a parametric sphere mesh.
`create_torus_mesh`	Creates a parametric torus mesh.
`estimate_principal_axis_within_radius`	Estimates the principal axis of points within a specified radius.
`estimate_principal_axes`	Computes the principal axes of an entire point cloud using PCA.
`filter_point_cloud_using_pass_through_filter`	Removes points outside a specified range along one axis.
`filter_point_cloud_using_bounding_box`	Keeps only points within an axis-aligned bounding box.
`filter_point_cloud_using_cylinder_base_removal`	Removes points belonging to a detected cylinder base.
`filter_point_cloud_using_mask`	Filters points using a boolean mask array.
`filter_point_cloud_using_oriented_bounding_box`	Keeps only points within an oriented bounding box.
`filter_point_cloud_using_plane_proximity`	Retains points within a distance threshold from a fitted plane.
`filter_point_cloud_using_plane_defined_by_point_normal_proximity`	Retains points near a plane defined by a point and normal vector.
`filter_point_cloud_using_plane_splitting`	Splits a point cloud into two halves along a plane.
`filter_point_cloud_using_radius_outlier_removal`	Removes points with too few neighbors within a given radius.
`filter_point_cloud_using_statistical_outlier_removal`	Removes statistical outliers based on mean distance to neighbors.
`filter_point_cloud_using_uniform_downsampling`	Reduces point count by keeping every nth point uniformly.
`filter_point_cloud_using_viewpoint_visibility`	Removes points not visible from a specified camera viewpoint.
`filter_point_cloud_using_voxel_downsampling`	Downsamples a point cloud by averaging points within voxel cells.
`add_point_clouds`	Merges two point clouds into one.
`subtract_point_clouds`	Removes points from one cloud that overlap with another.
`scale_point_cloud`	Scales a point cloud by a given factor.
`apply_transform_to_point_cloud`	Applies a rigid 4×4 transformation matrix to a point cloud.
`project_point_cloud_to_plane`	Projects all points onto a fitted plane.
`project_point_cloud_to_plane_defined_by_point_normal`	Projects all points onto a plane defined by a point and normal.
`reconstruct_mesh_using_convex_hull`	Reconstructs a surface mesh as the convex hull of a point cloud.
`reconstruct_mesh_using_poisson`	Reconstructs a watertight surface mesh using Poisson reconstruction.
`register_point_clouds_using_cuboid_translation_sampler_icp`	Aligns point clouds using ICP with a cuboid translation sampler initialization.
`register_point_clouds_using_fast_global_registration`	Aligns point clouds using Fast Global Registration for coarse alignment.
`register_point_clouds_using_point_to_plane_icp`	Refines point cloud alignment using point-to-plane ICP.
`register_point_clouds_using_point_to_point_icp`	Refines point cloud alignment using point-to-point ICP.
`register_point_clouds_using_rotation_sampler_icp`	Aligns point clouds using ICP with a rotation sampler initialization.
`segment_point_cloud_using_color`	Segments a point cloud into regions by color similarity.
`segment_point_cloud_using_plane`	Segments the dominant plane from a point cloud using RANSAC.

bash

python examples/vitreous_examples.py --example scale_point_cloud

Datatypes

List all available examples and run one:

bash

python examples/datatypes_examples.py --list

bash

python examples/datatypes_examples.py --example <name>

Example name	What it covers
`bool`	Demonstrates the Telekinesis boolean datatype.
`float`	Demonstrates the Telekinesis float datatype.
`int`	Demonstrates the Telekinesis integer datatype.
`float32`	Demonstrates the 32-bit float datatype.
`string`	Demonstrates the Telekinesis string datatype.
`rgba32`	Demonstrates the RGBA32 color datatype.
`image`	Demonstrates the Telekinesis image datatype.
`imageformat`	Demonstrates supported image format encodings.
`mat3x3`	Demonstrates the 3×3 matrix datatype.
`mat4x4`	Demonstrates the 4×4 transformation matrix datatype.
`vector3d`	Demonstrates the 3D vector datatype.
`vector4d`	Demonstrates the 4D vector datatype.
`points2d`	Demonstrates the 2D point array datatype.
`points3d`	Demonstrates the 3D point array datatype.
`points3d_list`	Demonstrates a list of 3D point arrays.
`boxes2d`	Demonstrates the 2D bounding box datatype.
`boxes3d`	Demonstrates the 3D bounding box datatype.
`mesh3d`	Demonstrates the 3D mesh datatype.
`linestrips2d`	Demonstrates the 2D line strip datatype.
`circles`	Demonstrates the circle geometry datatype.
`ellipses`	Demonstrates the ellipse geometry datatype.
`lines`	Demonstrates the line geometry datatype.
`channeldatatype`	Demonstrates the channel data type descriptor.
`colormodel`	Demonstrates the color model datatype.
`categories`	Demonstrates the category label datatype.
`object_detection_annotations`	Demonstrates bounding-box object detection annotation format.
`panoptic_segmentation_annotation`	Demonstrates panoptic segmentation annotation format.
`geometry_detection_annotations`	Demonstrates geometric shape detection annotation format.
`part`	Demonstrates the part datatype for object decomposition.
`tray`	Demonstrates the tray datatype for bin-picking scenes.
`bin`	Demonstrates the bin datatype for bin-picking scenes.

bash

python examples/datatypes_examples.py --example bool

Medulla

Each script is run directly with:

bash

python examples/medulla/<vendor>/<script>.py

Webcam

Script	What it covers
`quickstart.py`	Minimal example to capture a frame from a webcam.
`capture_image_example.py`	Captures a single image from a webcam.
`capture_video_example.py`	Captures a video stream from a webcam.
`camera_loop.py`	Continuously reads frames from a webcam in a loop.
`publish_video_example.py`	Publishes a webcam video stream over BabyROS.

bash

python examples/medulla/webcam/quickstart.py

IDS

Script	What it covers
`capture_image_example.py`	Captures a single image from an IDS camera.
`capture_video_example.py`	Captures a video stream from an IDS camera.
`camera_loop.py`	Continuously reads frames from an IDS camera in a loop.
`publish_video_example.py`	Publishes an IDS camera video stream over BabyROS.
`advanced_example.py`	Demonstrates advanced IDS camera configuration and capture.

bash

python examples/medulla/ids/capture_image_example.py

Synapse

Each script is run directly with:

bash

python examples/synapse/<script_or_subdir/script>.py

Quickstart

Script	What it covers
`quickstart_set_cartesian_pose_universal_robots.py`	Moves a Universal Robots arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_franka_robotics.py`	Moves a Franka Robotics arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_abb.py`	Moves an ABB robot arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_kuka.py`	Moves a KUKA robot arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_fanuc.py`	Moves a Fanuc robot arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_motoman.py`	Moves a Yaskawa Motoman arm to a target Cartesian pose.
`quickstart_set_cartesian_pose_neura_robotics.py`	Moves a Neura Robotics arm to a target Cartesian pose.
`quickstart_set_joint_positions_universal_robots.py`	Commands a Universal Robots arm to specific joint positions.
`quickstart_set_joint_positions_franka_robotics.py`	Commands a Franka Robotics arm to specific joint positions.
`quickstart_set_joint_positions_abb.py`	Commands an ABB robot arm to specific joint positions.
`quickstart_set_joint_positions_kuka.py`	Commands a KUKA robot arm to specific joint positions.
`quickstart_set_joint_positions_fanuc.py`	Commands a Fanuc robot arm to specific joint positions.
`quickstart_set_joint_positions_motoman.py`	Commands a Yaskawa Motoman arm to specific joint positions.
`quickstart_set_joint_positions_neura_robotics.py`	Commands a Neura Robotics arm to specific joint positions.

bash

python examples/synapse/quickstart_set_cartesian_pose_universal_robots.py

Connection and Disconnection

Script	What it covers
`connection_and_disconnection/connection_and_disconnection.py`	Demonstrates connecting to and disconnecting from a robot.

bash

python examples/synapse/connection_and_disconnection/connection_and_disconnection.py

Diagnostics

Script	What it covers
`diagnostics/get_speed_scaling_combined.py`	Reads the combined speed scaling factor applied by the controller.
`diagnostics/get_target_speed_fraction.py`	Reads the target speed fraction set for the robot program.

bash

python examples/synapse/diagnostics/get_speed_scaling_combined.py

Force Control

Script	What it covers
`force_control/is_tool_in_contact.py`	Detects whether the robot tool is currently in contact with an object.

bash

python examples/synapse/force_control/is_tool_in_contact.py

Kinematics

Script	What it covers
`kinematics/setup_kinematics_solver.py`	Initializes and configures the kinematics solver for a robot model.
`kinematics/forward_kinematics.py`	Computes end-effector pose from a given set of joint positions.
`kinematics/inverse_kinematics.py`	Solves joint positions for a target Cartesian end-effector pose.
`kinematics/inverse_kinematics_with_seed.py`	Solves IK starting from a user-provided seed configuration.
`kinematics/inverse_kinematics_with_profile.py`	Solves IK with a motion profile for smoother trajectory planning.
`kinematics/inverse_kinematics_collision_free.py`	Finds a collision-free IK solution for a target Cartesian pose.
`kinematics/get_link_transforms.py`	Retrieves the transformation matrices for each robot link.
`kinematics/set_default_joint_configuration.py`	Sets the default joint configuration used as IK seed.

bash

python examples/synapse/kinematics/setup_kinematics_solver.py

Motion

Script	What it covers
`motion/set_joint_positions.py`	Moves the robot to target joint positions.
`motion/set_joint_positions_advanced.py`	Moves to joint positions with advanced motion parameters.
`motion/set_joint_positions_with_visualization_example.py`	Moves to joint positions and visualizes the motion in Rerun.
`motion/set_joint_positions_advanced_with_visualization.py`	Advanced joint motion with Rerun visualization.
`motion/set_cartesian_pose.py`	Moves the end-effector to a target Cartesian pose.
`motion/set_cartesian_pose_advanced.py`	Moves to a Cartesian pose with advanced motion parameters.
`motion/set_cartesian_pose_with_visualization_example.py`	Moves to a Cartesian pose and visualizes in Rerun.
`motion/set_cartesian_pose_advanced_with_visualization.py`	Advanced Cartesian motion with Rerun visualization.
`motion/set_cartesian_pose_in_joint_space.py`	Reaches a Cartesian target via joint-space planning.
`motion/set_cartesian_pose_in_joint_space_advanced.py`	Advanced joint-space planning to a Cartesian target.
`motion/set_joint_position_in_cartesian_space.py`	Commands joint positions while tracking a Cartesian-space path.
`motion/contact_detection.py`	Detects contact events during robot motion.
`motion/move_until_contact.py`	Moves the robot along a direction until contact is detected.
`motion/start_and_stop_freedrive_mode.py`	Enables and disables freedrive (gravity-compensated hand-guiding) mode.
`motion/start_and_stop_jog_mode.py`	Enables and disables jog mode for incremental manual movement.
`motion/start_and_stop_teach_mode.py`	Enables and disables teach mode for recording robot poses.
`motion/stop_cartesian_motion.py`	Stops an ongoing Cartesian motion command.
`motion/stop_joint_motion.py`	Stops an ongoing joint motion command.
`motion/trigger_protective_stop.py`	Triggers a protective stop to safely halt the robot.

bash

python examples/synapse/motion/set_joint_positions.py

Robot Statuses

Script	What it covers
`robot_statuses/get_robot_status.py`	Reads the overall robot status.
`robot_statuses/get_robot_mode.py`	Reads the current robot operating mode.
`robot_statuses/get_runtime_state.py`	Reads the runtime execution state of the robot program.
`robot_statuses/get_safety_mode.py`	Reads the current safety mode of the robot.
`robot_statuses/get_controller_frequency.py`	Reads the control loop frequency of the robot controller.

bash

python examples/synapse/robot_statuses/get_robot_status.py

Servo Control

Script	What it covers
`servo_control/servo_joint.py`	Streams joint position targets at high frequency for servo control.
`servo_control/servo_cartesian.py`	Streams Cartesian pose targets at high frequency for servo control.
`servo_control/servo_circular.py`	Executes a circular trajectory using servo control.
`servo_control/servo_stop.py`	Stops an active servo motion.

bash

python examples/synapse/servo_control/servo_joint.py

State Reading

Script	What it covers
`state_reading/is_connected.py`	Checks whether the SDK is connected to the robot.
`state_reading/get_cartesian_pose.py`	Reads the current end-effector Cartesian pose.
`state_reading/get_joint_positions.py`	Reads the current joint positions.
`state_reading/get_joint_velocities.py`	Reads the current joint velocities.
`state_reading/get_joint_torques.py`	Reads the current joint torques.
`state_reading/get_actual_tcp_speed.py`	Reads the actual TCP (tool center point) speed.
`state_reading/get_actual_tcp_force.py`	Reads the actual force/torque at the TCP.
`state_reading/get_target_tcp_pose.py`	Reads the target TCP pose commanded to the controller.
`state_reading/get_target_tcp_speed.py`	Reads the target TCP speed commanded to the controller.
`state_reading/get_target_joint_positions.py`	Reads the target joint positions commanded to the controller.
`state_reading/get_target_joint_velocities.py`	Reads the target joint velocities commanded to the controller.
`state_reading/get_target_joint_accelerations.py`	Reads the target joint accelerations commanded to the controller.
`state_reading/get_timestamp.py`	Reads the robot controller timestamp.

bash

python examples/synapse/state_reading/is_connected.py

Tools

Script	What it covers
`tools/connnection_and_disconnection.py`	Connects to and disconnects from a robot tool (e.g. gripper).
`tools/get_current_position.py`	Reads the current position of a robot tool.
`tools/open.py`	Opens a robot tool (e.g. gripper).
`tools/close.py`	Closes a robot tool (e.g. gripper).
`tools/move.py`	Moves a robot tool to a specified position.
`tools/set_speed.py`	Sets the movement speed of a robot tool.
`tools/set_force.py`	Sets the gripping force of a robot tool.
`tools/set_position_range.py`	Configures the position range limits of a robot tool.
`tools/set_unit.py`	Sets the measurement units used by a robot tool.

bash

python examples/synapse/tools/connnection_and_disconnection.py

Visualization and Model

Script	What it covers
`visualization_and_model/get_model.py`	Retrieves the robot's kinematic model.
`visualization_and_model/get_visual_model.py`	Retrieves the robot's visual mesh model.
`visualization_and_model/get_collision_model.py`	Retrieves the robot's collision geometry model.
`visualization_and_model/get_link_transforms.py`	Retrieves transformation matrices for each robot link from the visual model.
`visualization_and_model/get_visual_meshes_data.py`	Retrieves raw mesh data for all visual meshes.
`visualization_and_model/get_visual_mesh_transforms.py`	Retrieves transformation matrices for all visual meshes.

bash

python examples/synapse/visualization_and_model/get_model.py

Where to Go Next

Applications

Real-world use cases: pick-and-place, palletizing, quality inspection, and more.

Explore the Docs

Skills

Vision, 3D, hardware, and robotics skills — the full API reference.

Agents

Turn natural-language instructions into robot code with Tzara, the VS Code agent.

Data Engine

Generate and manage synthetic datasets for training Physical AI models.

BabyROS

Lightweight pub/sub and service primitives for building robot communication layers.

Applications

Real-world use cases: pick-and-place, palletizing, quality inspection, and more.

Support

Join Discord

Ask questions, share what you're building, and get help from the community.

Add a Skill?

Have a new Skill to be added to Telekinesis? Get in touch with us.

Telekinesis Skill Examples ​

Run an Example! ​

Clone the repository and the telekinesis-data submodule ​

Install dependencies for examples ​

Run an example (see more examples below) ​

Cornea ​

Pupil ​

Vitreous ​

Datatypes ​

Medulla ​

Webcam ​

IDS ​

Synapse ​

Quickstart ​

Connection and Disconnection ​

Diagnostics ​

Force Control ​

Kinematics ​

Motion ​

Robot Statuses ​

Servo Control ​

State Reading ​

Tools ​

Visualization and Model ​

Where to Go Next ​

Explore the Docs ​

Support ​

Telekinesis Skill Examples

Run an Example!

Clone the repository and the `telekinesis-data` submodule

Install dependencies for examples

Run an example (see more examples below)

Cornea

Pupil

Vitreous

Datatypes

Medulla

Webcam

IDS

Synapse

Quickstart

Connection and Disconnection

Diagnostics

Force Control

Kinematics

Motion

Robot Statuses

Servo Control

State Reading

Tools

Visualization and Model

Where to Go Next

Explore the Docs

Support