Telekinesis Agentic Skill Library

Appearance

Developer Quickstart ​

Lets Build!

Get up and running with the Telekinesis SDK and run your first example in just a few minutes.

Step 1: Create an API Key ​

Create a Telekinesis account and generate an API key:

Create a Telekinesis account!

alt text

Store the key in a safe location, such as your shell configuration file (e.g. .zshrc, .bashrc) or another secure location on your computer.

Step 2: Configure the API Key ​

Export the API key as an environment variable.

Open a terminal window and run below command as per your OS system.

Replace <your_api_key> with the one generated in Step 1.

bash
export TELEKINESIS_API_KEY="<your_api_key>"
powershell
setx TELEKINESIS_API_KEY "<your_api_key>"

WARNING

For Windows, after running setx, restart the terminal for the changes to take effect.

Optionally verify that the key is set:

bash
echo $TELEKINESIS_API_KEY
powershell
echo $Env:TELEKINESIS_API_KEY

The Telekinesis SDK uses this API key to authenticate requests and automatically reads it from your system environment.

Step 3: Install the Telekinesis SDK ​

  1. Create an isolated environment so that there is no dependency conflicts. We recommend installing Miniconda environment by following instructions from here.

  2. Create a new conda environment called telekinesis:

bash
conda create -n telekinesis python=3.11
  1. Activate the environment:
bash
conda activate telekinesis
  1. Install the core SDK using pip:

We currently support Python versions - 3.11, 3.12. Ensure your environment is in the specified Python version.

bash
pip install telekinesis-ai

Step 4: Run Your First Example ​

  1. Git clone our telekinesis-examples repository from Github with:
bash
git clone --depth 1 --recurse-submodules --shallow-submodules https://github.com/telekinesis-ai/telekinesis-examples.git

INFO

This also downloads the telekinesis-data repository, which contains sample data used by the examples. You can replace this with your own data when using Telekinesis in your own projects. Download time may vary depending on your internet connection.

  1. Change directory into telekinesis-examples:
bash
cd telekinesis-examples
  1. Install example-only dependencies:
bash
pip install numpy scipy opencv-python rerun-sdk==0.27.3 loguru
  1. Run the segment_image_using_sam example:
bash
python examples/cornea_examples.py --example segment_image_using_sam

If the example runs successfully, a Rerun visualization window will open showing the result.

INFO

Rerun is a visualization tool used to display 3D data and processing results.

Rerun Visualization

Sam Segmentation Demonstration

Step 5: Explore More Examples ​

We provide a large set of examples to help you learn all the available skills in the SDK.

Find the complete list with:

bash
python examples/cornea_examples.py --list

This will display all available examples, such as:

To run any of the above examples, replace <name_of_example> below with names from the list generated above such as segment_image_using_ycrcb, segment_image_using_foreground_birefnet:

bash
python examples/cornea_examples.py --example <name_of_example>

INFO

You can explore our GitHub repositories using the links below:

Where To Go Next? ​

Now that you’ve successfully run your first example, you’re ready to build with Telekinesis.

Use Telekinesis in Your Project ​

Learn how to integrate the SDK into your own code through the use of Telekinesis Skills.

Curious how data flows through Telekinesis? ​

Explore the datatypes_examples to understand how data is represented, passed, and transformed between Skills.