Browse by type

If you have any questions related to the solver, visit the GitHub Discussions page. This guarantees accessibility for everyone.
The documentation is available at tinympc.org
High-level language interfaces with detailed examples and code generation are available in Python, Julia, and MATLAB.
Excited to hear your TinyMPC success stories, share them with us!
For Windows - Enable wsl before following prompts below
git clone https://github.com/TinyMPC/TinyMPC.git
cd TinyMPC && mkdir build && cd build
cmake ..
cmake --build .
quadrotor_hovering example./examples/quadrotor_hovering
codegen_cartpole example then follow the same building steps inside that directory./examples/codegen_cartpole
If you are using TinyMPC, we encourage you to
Put a star ⭐ on this repository.
Cite the related papers:
@inproceedings{tinympc,
title={TinyMPC: Model-Predictive Control on Resource-Constrained Microcontrollers},
author={Khai Nguyen and Sam Schoedel and Anoushka Alavilli and Brian Plancher and Zachary Manchester},
booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
year={2024},
}
@inproceedings{tinympc-adaptive,
title={Robust and Efficient Embedded Convex Optimization through First-Order Adaptive Caching},
author={Ishaan Mahajan and Brian Plancher},
booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
year={2025},
}
@inproceedings{conic-tinympc,
title={Code Generation and Conic Constraints for Model-Predictive Control on Microcontrollers with Conic-TinyMPC},
author={Ishaan Mahajan and Khai Nguyen and Sam Schoedel and Elakhya Nedumaran and Moises Mata and Brian Plancher and Zachary Manchester},
booktitle={IEEE International Conference on Robotics and Automation (ICRA)},
year={2026},
}
Please report any issues via the Github issue tracker. All types of issues are welcome including bug reports, documentation typos, feature requests and so on.
Numerical benchmarks against other solvers on MCUs are available here.
TinyMPC-integrated firmware on the Crazyflie nano-quadrotor is available here.
An earlier version (not optimized) which can deal with nonlinear dynamics (e.g., bicycle models) is available here.
$ claude mcp add TinyMPC \
-- python -m otcore.mcp_server <graph>