{"id":"fe8e8e84-03cc-4745-8644-5729890a4103","slug":"octo","name":"Octo","description":"Open-source generalist robot policy developed at UC Berkeley/Stanford. Transformer-based diffusion policy trained on 800K trajectories from the Open X-Embodiment dataset. Supports multi-robot and language-conditioned manipulation tasks. 27M and 93M parameter variants.","brainType":"research-model","isOpen":true,"maturityStage":"research","architecture":"Transformer diffusion policy, 27M/93M params","reviewStatus":"reviewed","sources":[{"url":"https://octo-models.github.io/","date":"2024-01-01","title":"Octo: An Open-Source Generalist Robot Policy","sourceName":"Octo Model Team"},{"url":"https://github.com/octo-models/octo","title":"Octo open source repository","sourceName":"Octo Model Team"},{"url":"https://octo-models.github.io/paper.pdf","title":"Octo: An Open-Source Generalist Robot Policy","sourceName":"Octo Model Team"},{"url":"https://arxiv.org/html/2405.12213v2","title":"Octo: An Open-Source Generalist Robot Policy","sourceName":"Octo Model Team"}],"keyFacts":[{"label":"Octo model and data (primary project page)","value":"The Octo project page describes Octo as a transformer-based diffusion policy pretrained on 800k robot episodes from the Open X-Embodiment dataset, trained on a mixture of 25 datasets. It introduces Octo-Small (27M parameters) and Octo-Base (93M parameters). Authors are affiliated with UC Berkeley, Stanford, Carnegie Mellon, and Google DeepMind. The citation is Robotics: Science and Systems 2024, Delft (Octo project page)"},{"label":"Reported zero-shot and finetune results (primary project page)","value":"The same page reports zero-shot success of 0.50 on WidowX, 0.70 on UR5, and 0.80 on the RT-1 robot, and an average finetune success of 0.72 across six setups that each use about 100 target demonstrations, versus 0.20 from scratch. Treat these as paper-reported evaluation rates, not a deployed fleet census (Octo project page)"},{"label":"Open source code and checkpoints","value":"The Octo project links an open source repository with model code, pretrained checkpoints, and fine tuning materials for the Octo generalist robot policy (Octo repository)"},{"label":"Flexible task and observation interface","value":"The Octo project describes a policy designed to accept flexible task and observation definitions and adapt to new robotic platforms through fine tuning (Octo project)"},{"label":"Generalist policy architecture","value":"The Octo team describes Octo as a transformer-based diffusion policy for broadly applicable robotic manipulation (Octo)."},{"label":"Pretraining corpus","value":"The Octo team says the model was pretrained on 800,000 robot episodes from the Open X-Embodiment dataset (Octo)."},{"label":"Multimodal conditioning","value":"The Octo team says Octo supports natural-language instructions, goal images, observation histories, and multimodal action distributions (Octo)."},{"label":"Fine-tuning flexibility","value":"The Octo team says the policy can be fine-tuned to new observation and action spaces and different robot setups (Octo)."},{"label":"Published model sizes","value":"The Octo project identifies Octo-Small at 27 million parameters and Octo-Base at 93 million parameters (Octo)."}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-09T14:35:25.068Z","updatedAt":"2026-10-09T22:00:42.471Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/octo","url":"https://registry.deploy.report/brains/octo","name":"Octo","description":"Open-source generalist robot policy developed at UC Berkeley/Stanford. Transformer-based diffusion policy trained on 800K trajectories from the Open X-Embodiment dataset. Supports multi-robot and language-conditioned manipulation tasks. 27M and 93M parameter variants.","identifier":"fe8e8e84-03cc-4745-8644-5729890a4103","applicationCategory":"research-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"research","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":4,"primary_source_types":["code-repository","preprint"]}}}