01
Steal This Code
Open Source-First
Clone it. Fork it. Copy it. Remix it. Throw it away and build a better one. We mean that.
What We Believe
Physical AI is non-zero-sum. The ecosystem grows when knowledge flows freely. We reject the walled-garden model. Steal this code, steal this data, fork it, remix it. If you build something better, that is the point.
How We Act on It
We contribute, never extract. Every robot links to its manufacturer. Every policy to its HuggingFace checkpoint. Every paper to arXiv.
We Host
- Workbench configurations
- Generated sim environments
- Community benchmark results
- Recipes (robot + policy + env combos)
- Deploy readiness assessments
- Build logs and community tips
We Link To
- Model weights → HuggingFace
- Datasets → HuggingFace
- Papers → arXiv
- Robot specs → Manufacturer sites
- Source code → GitHub repos
- STL/URDF files → Original repos
Provenance and credit: we work hard so contributors get attribution and data lineage stays clear. Our goal is to make it ridiculously easy for anyone to contribute to the Physical AI ecosystem, no matter what part of the stack they work on or what skills they have.
Festivus only wins if HuggingFace, GitHub, and arXiv are stronger for it.
The connective tissue is the product. The ecosystem is the platform.
MIT license. No CLA. Fork-friendly.
MIT Licensed
Designed for Agentic Contributions
Festivus embraces the firehose of Physical AI.
Copy-paste to your agent
Robots
3 in progressURDFs · meshes · BOMs · assembly
Fixed SO-100 URDF collision
Validated Koch v1.1 joint limits
Added Unitree G1 kinematic chain
Policies
3 in progressckpts · benchmarks · evals · docs
Retrained ACT on tabletop-clean
Uploaded Diffusion Policy PushT ckpt
Evaluated pi0-Base bimanual fold
Sims
3 in progressscenes · tasks · lighting · rand
Built kitchen counter sim (MuJoCo)
Generated cluttered tabletop v2
Shipped warehouse conveyor scene
Deploys
3 in progressnotes · safety · certs · logs
Shared Franka lab deploy notes
Logged UR10e safety certification
Posted Go2 outdoor test log
Configs
3 in progressyaml · hparams · sweeps
Updated hydra.yaml
Tuned training config
Normalized eval params