Generalist diffusion policy

Octo

Octo is a generalist robot policy designed for adaptation to different observation and action spaces, with language or goal-image conditioning.

Source contextPrimary specReviewed 2026-09-28

Sources 2

octo-models/octo official repository

octo-models · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Octo research project

Octo research team · Publication date not disclosed · Source accessed 2026-09-28

Reviewed recordLast reviewed 2026-09-282 sources ↗4 sourced fields

Official source Suggest a correction

Architecture and scope

A transformer consumes robot observations and a diffusion policy produces actions. The project supplies pretrained variants and fine-tuning tools instead of claiming that all robot hardware shares one ready-to-run controller.

Source contextPrimary specReviewed 2026-09-28

Sources 2

octo-models/octo official repository

octo-models · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Octo research project

Octo research team · Publication date not disclosed · Source accessed 2026-09-28

Integration and evaluation

Adaptation can introduce different sensory inputs, action interfaces and robot morphologies. This is useful when evaluating an existing data collection pipeline against the model’s preprocessing and output conventions.

Source contextPrimary specReviewed 2026-09-28

Sources 2

octo-models/octo official repository

octo-models · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Octo research project

Octo research team · Publication date not disclosed · Source accessed 2026-09-28

Evidence boundary

Fine-tuned embodiments and training data differ; benchmark numbers require their exact configuration.

Source contextPrimary specReviewed 2026-09-28

Sources 2

octo-models/octo official repository

octo-models · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Octo research project

Octo research team · Publication date not disclosed · Source accessed 2026-09-28

Model identity

Developer: Octo research team
Primary specReviewed 2026-09-28
Sources 1
octo-models/octo official repository
octo-models · Publication date not disclosed · Source accessed 2026-09-28
Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.
Exact version / scope: Octo-Base and Octo-Small
Primary specReviewed 2026-09-28
Sources 1
octo-models/octo official repository
octo-models · Publication date not disclosed · Source accessed 2026-09-28
Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.
Category: Generalist diffusion policy
Primary specReviewed 2026-09-28
Sources 1
octo-models/octo official repository
octo-models · Publication date not disclosed · Source accessed 2026-09-28
Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.
Access model: Public pretrained checkpoints and code
Primary specReviewed 2026-09-28
Sources 1
octo-models/octo official repository
octo-models · Publication date not disclosed · Source accessed 2026-09-28
Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.
License: Not publicly disclosed

Inputs, outputs & embodiment

Inputs: Not publicly disclosed
Outputs: Not publicly disclosed
Embodiment: Not publicly disclosed

Implementation & training

Compute: Not publicly disclosed
Training-data disclosures: Not publicly disclosed
Integrations: Not publicly disclosed

Reported benchmark results

Context before scores. Results from different benchmarks are not directly comparable. A simulation result does not establish real-world reliability, safety or commercial availability.

No result meets our complete revision and methodology requirements for this record yet. Inspect the original benchmark documentation before comparing published scores.

What this evidence does not establish

Fine-tuned embodiments and training data differ; benchmark numbers require their exact configuration.
Pricing and deployment service terms were not verified.

Relationships & deployments

Related reading is an editorial crosslink. Sourced connections describe relationships reported in the cited material. A link to a versioned profile does not establish compatibility with that version unless the connection note explicitly identifies it.

Record history & verified changes

A research review records when we checked a source. It does not mark a product launch or a new deployment.

Initial reviewed record. No subsequent field change has been recorded.

Inspect the evidence

Sources & evidence

md-octo

octo-models/octo official repository

octo-models · Repository · Publication date not disclosed · Source accessed 2026-09-28

License: MIT code. Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Referenced by 1 record: Octo

md-octo-project

Octo research project

Octo research team · Paper · Publication date not disclosed · Source accessed 2026-09-28

Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Referenced by 1 record: Octo