GitHub  •  LinkedIn  •  X  •  Discord

Telekinesis Agentic OS

Telekinesis is the Agentic OS for general-purpose robots. It provides a unified Python library that brings the entire Physical AI stack together: Vision-Language-Action models, World Models, perception, planning, hardware interfaces, and more.

Learn more about all available modules in detail in docs.telekinesis.ai. Join our Discord community to connect, share, and build together.

Release Model

Telekinesis Agentic OS library is currently in active development (pre-1.0).
Modules are introduced incrementally, and the API may evolve between minor releases.
To ensure compatibility and access to the latest capabilities, always install or upgrade to the most recent version of the package.

Currently available modules:

• cornea
• retina
• pupil
• vitreous
• medulla
• synapse
• babyros
• datatypes
• isaacsim
• axon
• tf

Getting Started

Telekinesis SDK requires a free API key to authenticate requests.

Create one at platform.telekinesis.ai. See the Quickstart for more details on the generation of API key.

Installation

Core 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:

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

   conda create -n telekinesis python=3.11
   

3. Activate the environment:

   conda activate telekinesis
   

4. Install the core SDK using pip:

   pip install telekinesis-ai
   

   Note: The Python module is called telekinesis, while the package published on PyPI is telekinesis-ai.

medulla

medulla is a module in the Telekinesis SDK for connecting to cameras and hardware devices. It is installed by default as part of telekinesis-ai, with webcam support included out of the box:

pip install telekinesis-ai

In order to install vendor specific dependencies, please follow the official documentation on https://docs.telekinesis.ai/medulla/overview.html, e.g. for using IDS cameras with medulla:

pip install telekinesis-ai[medulla-ids]

You can find the list of supported vendors in the overview section under supported cameras.

See the official medulla documentation for more details about the installation.

IDS cameras: Installing the ids extras (pip install telekinesis-ai[medulla-ids]) fetches ids_peak, ids_peak_ipl, and ids_peak_icv directly from IDS Imaging Development Systems GmbH's own PyPI distribution. By installing these packages, you become the licensee under the IDS Software Suite License Terms and are bound by its conditions.

RealSense cameras: Installing the realsense extras (pip install telekinesis-ai[medulla-realsense]) fetches pyrealsense2 directly from Intel's PyPI distribution. By installing this package, you become the licensee under the Intel RealSense SDK 2.0 License Terms and are bound by its conditions.

synapse

synapse is a module in the Telekinesis SDK for controlling and communicating with industrial robot manipulators and tools. It provides a unified API across multiple robot and tool brands. It is installed by default as part of telekinesis-ai.

Robot support:

• Offline (simulation): all supported robots
• Real-world (hardware control): Universal Robots only

Supported platforms: Windows, macOS

synapse depends on telekinesis-urdfs for robot model data, which must be installed before telekinesis-ai.

1. Install telekinesis-urdfs:

   git clone --depth 1 https://github.com/telekinesis-ai/telekinesis-urdfs.git
   cd telekinesis-urdfs
   pip install .
   

   Note: telekinesis-urdfs is a large repository containing robot model data. The initial clone and wheel build are expected to take several minutes — do not interrupt the process.

2. Install telekinesis-ai (which includes synapse):

   pip install telekinesis-ai
   

See the official synapse documentation for more details about the installation and supported robots.

isaacsim

isaacsim is currently under active development. It is a module in the Telekinesis SDK for connecting to NVIDIA Isaac Sim through the Telekinesis Isaac Sim bridge (a Python client built on a C++ core). It is an optional dependency — install it with the isaacsim extra:

pip install telekinesis-ai[isaacsim]

Supported platforms: Windows (macOS and Linux support coming soon)

Example

Important: TELEKINESIS_API_KEY is required for the below to run successfully.

Vision Module

Run below to test retina module:

from telekinesis import retina, datatypes

image_url = "https://assets.telekinesis.ai/examples/v1/images/palletizing.jpg"
image = datatypes.Image.from_url(url=image_url)

detection_results, categories = retina.detect_objects_using_grounding_dino(
    image=image,
    objects=["carton"],
    box_threshold=0.45,
    text_threshold=0.5,
)

detection_results

IsaacSim

Run below to test isaacsim_client connection:

from telekinesis.isaacsim_client import IsaacSimClient

client = IsaacSimClient(
    api_key="",
    base_url="http://127.0.0.1:8766",
    websocket_base_url="ws://127.0.0.1:8766",
)

created = client.articulation.create("/World/ur10e")
print(created["articulation_id"])

client.articulation.set_joint_positions(created["articulation_id"], [0.0] * created["num_dof"])

More examples are available on Telekinesis Isaac Sim Examples

Resources

• All module examples are available in Telekinesis Examples
• Full SDK documentation and usage details: Telekinesis Documentation

Support

For issues and questions:

• Create an issue in the GitHub repository.
• Contact the Telekinesis development team at support@telekinesis.ai or on Discord.