Welcome to the Monty Repository!

An open-source, sensorimotor learning system following the principles of the neocortex.

This repository contains the first implementation of a sensorimotor learning system from the Thousand Brains Project. We lovingly call it Monty after Vernon Mountcastle, who proposed cortical columns as a repeating functional unit across the neocortex.

This is an open-source project that was initially started at Numenta. The Thousand Brains Project is now an independent non-profit, partially funded by the Gates Foundation.

Please find our full documentation here

Our API documentation here.

Getting Started

You can find detailed instructions on how to install the project requirements and how to get started here

Current Performance

We regularly evaluate this system against a set of sensorimotor tasks, and report results in benchmark experiments. Any time a functional change is made to the code, these experiments are rerun, and results are updated. Configs for these experiments can be found in the src/tbp/monty/conf/experiment/ folder.

You can find our current performance on these benchmarks as well as an explanation of them here.

Contributing

Are you interested in contributing? Check out our tips and guidelines here.

Before contributing, please sign our Contributor License Agreement (CLA). You can find the CLA and guidelines here.

Disclaimer

This is not production-ready code. It is an early beta version that is under active development. This early beta version is functional but evolving. Expect frequent changes as we develop core features.

You can find a list of the systems current capabilities and application criteria here.

You can find our project road map and details on the next features we are working on here.

More Information and Updates

As mentioned above, we have extensive documentation of this project here.

We also publish our meeting recordings on YouTube on the Thousand Brains Project channel.

If you want to use this code, contribute to it, ask questions or propose ideas, please consider joining our discourse channel.

If you would like to receive updates, follow us on Bluesky or Twitter or LinkedIn.

If you have further questions or suggestions for collaborations, don't hesitate to contact us directly at info@thousandbrains.org.

Citing the Project

If you're writing a publication that references the Thousand Brains Project, please cite

TBP white paper:

@misc{thousandbrainsproject2024,
      title={The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence},
      author={Viviane Clay and Niels Leadholm and Jeff Hawkins},
      year={2024},
      eprint={2412.18354},
}

If you would like to refer to Monty's capabilities and advantages over deep learning, please cite

Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference:

@article{thousand-brains_systems_2026,
	title = {Thousand-{Brains} {Systems}: {Sensorimotor} {Intelligence} for {Rapid}, {Robust} {Learning} and {Inference}},
	volume = {38},
	issn = {0899-7667, 1530-888X},
	url = {https://direct.mit.edu/neco/article/38/6/845/136222/Thousand-Brains-Systems-Sensorimotor-Intelligence},
	doi = {10.1162/NECO.a.1508},
	number = {6},
	urldate = {2026-06-10},
	journal = {Neural Computation},
	author = {Leadholm, Niels and Clay, Viviane and Knudstrup, Scott and Lee, Hojae and Hawkins, Jeff},
      month = may,
	year = {2026},
	pages = {845--896},
}

If you would like to reference the theory behind this novel AI approach, here you can find a list of neuroscience theory papers.

License

The MIT License. See the LICENSE for details.