Skip to main content
EmbodiK logo

EmbodiK

Python C++ Nanobind Build PyPI Docs License: Apache-2.0 GitHub stars

EmbodiK is a high-performance prioritized numerical inverse kinematics library for cross-embodiment robotics and VLA/AI applications. It pairs a C++ core with Python bindings, exposes robot-model utilities without requiring the Python pin package at runtime, and includes interactive examples for collision-aware IK, CoM constraints, teleop, whole-body robots, GPU batch solving, and dual-arm coordination.

✨ Overview

EmbodiK is designed for bringing up IK behavior across different robot bodies without rewriting the solver stack for each model. The public examples focus on a practical path:

  • 🧭 start with the smallest fixed-base IK loop.
  • 🛡️ add collision, joint-limit, and CoM constraints.
  • 🎮 connect the same prioritized IK solver path to teleop input.
  • 🤖 scale to bimanual, humanoid, and Spot whole-body examples.
  • 🧪 use richer clone-only examples for development, stress testing, and policy rollout.

The intent is to keep Python examples lean: visualization and target plumbing stay in Python, while constraint handling and recovery policy stay in the C++ solver.

The detailed installation notes, API reference, and example walkthroughs live in the official documentation:

https://robodreamer.github.io/embodik/

🚀 Quick Start

Fastest path for most users is the wheel-only PyPI install inside a virtual environment:

python -m venv .venv
source .venv/bin/activate
python -m pip install -U pip
python -m pip install --only-binary=:all: embodik
python -c "import embodik; print(embodik.__version__)"

If that import works, the core package is installed. Copy the examples and run the fixed-base loop:

python -m pip install "embodik[examples]"
embodik-examples --copy
cd embodik_examples
python 01_basic_ik_simple.py

If pip cannot find a compatible wheel, use the one-shot source installer for your platform from the Installation Guide. It creates the venv, installs native dependencies, builds EmbodiK, and runs an import smoke test.

Published repaired wheels do not require the Python pin package at runtime. Source builds use pin or a system Pinocchio install as the native library provider; keep that provider installed in the environment used to import EmbodiK.

⚡ Experimental GPU whole-body IK

The animation is the default 512-world viewer. The measured reference scale is 1,024 worlds (--worlds 1024), which is a separate run from this preview.

Panda, ROBOTIS AI Worker, and Unitree G1 moving through distinct trajectories across 512 fully articulated CUDA worlds

embodik.gpu.wbc is experimental and opt-in. The CPU solver remains the stable default. The GPU path derives joint and task dimensions from the loaded model, including Panda, AI Worker, and G1. There is no silent CPU fallback.

From a source checkout:

pixi run setup-gpu-wbc
pixi run -e cuda demo-parallel-tracking

The viewer opens at http://localhost:8080. Device memory, model switches, the 1,024-world latency table, and how those samples were measured are in the GPU WBC guide. The parallel example guide covers headless profiling and RL integration.

🎮 Examples

01_basic_ik_simple.py is the minimal fixed-base bring-up for a robot preset or a new URDF. Most scripts default to the Panda preset. Collision, teleop, CoM, dual-arm coordination, bimanual and humanoid whole-body control, Spot, and the GPU batch demo are listed in the Examples Guide, including Seer controller ports and the mjviser policy flags.

🎬 Preview

Franka Panda collision-free IK

Franka Panda collision-free IK preview

ROBOTIS AI Worker constraint teleop

ROBOTIS AI Worker constraint teleop preview

RB-Y1 bimanual whole-body IK

RB-Y1 bimanual whole-body IK preview

Unitree G1 retargeting IK

Unitree G1 retargeting IK preview

Spot full-body IK

Spot full-body IK preview

Spot locomanipulation mjviser

Spot locomanipulation mjviser preview

🧰 Core Capabilities

  • ⚙️ C++ IK core with Nanobind Python bindings.
  • 🎯 Hierarchical velocity IK tasks for frames, posture, CoM, and dual-arm coordination.
  • 🧮 Fixed-base acceleration eSNS with compatible position, velocity, acceleration, effort, contact-kinematics, and geometry constraints.
  • 🛡️ Joint-limit, self-collision, and CoM support-polygon constraints.
  • 📈 Solver diagnostics for timing, task scaling, and Jacobian condition-number logging.
  • 🧭 Lie-group-aware configuration operations for floating-base, quaternion, and continuous joints.
  • 🤖 Native Pinocchio-backed robot model utilities exposed through EmbodiK bindings.
  • 👁️ Optional Viser visualization for interactive IK demos.
  • ⚡ Model-derived Newton/Warp GPU WBC with device-resident multi-world state, CUDA graph execution, collision constraints, task priority, posture, torso, and centroidal features.

📚 Documentation

  • Installation - platform setup, source builds, and troubleshooting.
  • Quickstart - first IK calls and solver concepts.
  • Acceleration Solver - fixed-base scope, state-box semantics, and collision certification boundaries.
  • Working with Transforms - transform helpers and SE(3) operations.
  • Examples - public scripts and development-only demos.
  • API Reference - Python API generated from docstrings.
  • GPU WBC - Newton/Warp setup, model compatibility, constraint coverage, batching, and performance methodology.
  • Development - local build, tests, and contributor workflow.

🛠️ Development

Use Pixi from a repository clone:

pixi run build
pixi run test
pixi run docs-build

Run examples from the clone:

pixi run python examples/01_basic_ik_simple.py
pixi run python examples/02_collision_aware_IK.py
pixi run python examples/03_teleop_ik.py

🗂️ Repository Layout

embodik/
|-- README.md
|-- cpp_core/
|   |-- include/embodik/
|   `-- src/
|-- python_bindings/
|   `-- src/
|-- python/embodik/
|-- examples/
|-- docs/
|-- scripts/
`-- test/

⭐ Star History

Star History Chart

📄 License

EmbodiK is released under the Apache License 2.0. See LICENSE for details. Binary wheels may bundle permissively licensed native dependencies; see THIRD_PARTY_NOTICES.md. Cite the project with CITATION.cff.

Developer: Andy Park andypark.purdue@gmail.com

Metadata

Release files for embodik 0.23.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for embodik 0.23.2
File Size Uploaded Provenance Actions
embodik-0.23.2.tar.gz 37.7 MB With provenance Details for embodik-0.23.2.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for embodik 0.23.2
File Actions
embodik-0.23.2-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details for embodik-0.23.2-cp312-cp312-manylinux_2_28_x86_64.whl
embodik-0.23.2-cp312-cp312-macosx_14_0_arm64.whl CPython 3.12 CPython 3.12 macOS 14.0+ ARM64 Details for embodik-0.23.2-cp312-cp312-macosx_14_0_arm64.whl
embodik-0.23.2-cp311-cp311-manylinux_2_28_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.28+ x86-64 Details for embodik-0.23.2-cp311-cp311-manylinux_2_28_x86_64.whl
embodik-0.23.2-cp311-cp311-macosx_14_0_arm64.whl CPython 3.11 CPython 3.11 macOS 14.0+ ARM64 Details for embodik-0.23.2-cp311-cp311-macosx_14_0_arm64.whl
embodik-0.23.2-cp310-cp310-manylinux_2_28_x86_64.whl CPython 3.10 CPython 3.10 Linux glibc 2.28+ x86-64 Details for embodik-0.23.2-cp310-cp310-manylinux_2_28_x86_64.whl
embodik-0.23.2-cp310-cp310-macosx_14_0_arm64.whl CPython 3.10 CPython 3.10 macOS 14.0+ ARM64 Details for embodik-0.23.2-cp310-cp310-macosx_14_0_arm64.whl

Total release size: 263.3 MB

Release files / embodik-0.23.2.tar.gz

Download URL embodik-0.23.2.tar.gz
Size 37.7 MB
Tags Source
SHA-256 checksum
How to use checksums
30c412945c2a0d86252bd7e81447b45714983897cb009dfe1eee28dfd84ff4d0
BLAKE2b-256 checksum
How to use checksums
cf6ebe19548da81964374ee13dca54b531adad24626f5021a4389a013ddf09a9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp312-cp312-manylinux_2_28_x86_64.whl

Download URL embodik-0.23.2-cp312-cp312-manylinux_2_28_x86_64.whl
Size 29.5 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
f4bf93eb6668de13e20c215b493b82c1ba5fc71e16ee292bb633466580ff8124
BLAKE2b-256 checksum
How to use checksums
4d844eba817028ab91202a3c5c83bd67866edc29ec2c78944ca16fb015440cac
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp312-cp312-macosx_14_0_arm64.whl

Download URL embodik-0.23.2-cp312-cp312-macosx_14_0_arm64.whl
Size 45.7 MB
Tags CPython 3.12 macOS 14.0+ ARM64
SHA-256 checksum
How to use checksums
80701764f6b0c4b8804b24d746e60f0540e4d2a388032f9f9c497e47b5022442
BLAKE2b-256 checksum
How to use checksums
cd4c105613af07bb0dc0f7ad6dc15edf498d3786cad8384b20ea094f4c973ee7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp311-cp311-manylinux_2_28_x86_64.whl

Download URL embodik-0.23.2-cp311-cp311-manylinux_2_28_x86_64.whl
Size 29.5 MB
Tags CPython 3.11 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
26005a59dce79063ba7de09ee779b085a4ab3c73ae5495fb8ebf06304da4bdc3
BLAKE2b-256 checksum
How to use checksums
9d6c1f92e27bd72247acc5895903976436003a74871f7033edee418f1064d900
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp311-cp311-macosx_14_0_arm64.whl

Download URL embodik-0.23.2-cp311-cp311-macosx_14_0_arm64.whl
Size 45.7 MB
Tags CPython 3.11 macOS 14.0+ ARM64
SHA-256 checksum
How to use checksums
12d4d79c79b59045494940f034072ff923aeec48636bbabfd1cff316365aee38
BLAKE2b-256 checksum
How to use checksums
029b9891b32d8af7cd97e283c7802e194193d90beecd6562cc4cf2552fb549f2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp310-cp310-manylinux_2_28_x86_64.whl

Download URL embodik-0.23.2-cp310-cp310-manylinux_2_28_x86_64.whl
Size 29.5 MB
Tags CPython 3.10 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
4a418299e3ae48688e9cbad3b6ea7964ac9e26f4277a765928a1235ffbc38bf6
BLAKE2b-256 checksum
How to use checksums
685e0f0f3edca82781742796e8e758f80fbb5ac54f43d89a52c6e658acdd8fa6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Release files / embodik-0.23.2-cp310-cp310-macosx_14_0_arm64.whl

Download URL embodik-0.23.2-cp310-cp310-macosx_14_0_arm64.whl
Size 45.7 MB
Tags CPython 3.10 macOS 14.0+ ARM64
SHA-256 checksum
How to use checksums
cc5907877dc62982e4ec375d58fb2383f45e1bd43cf3ad8df29493f57bd337a2
BLAKE2b-256 checksum
How to use checksums
31e1742f5f689b15671a51cd61600f61618e09d103cce3e3c973a87835b094f2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

Security for embodik 0.23.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 7 files in this release have been uploaded with provenance metadata.

Select from 7 files

Attestation for embodik-0.23.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 19, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.23.2 This release

7 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page