{"id":"e26cbf32-1225-4222-ad6e-cbf986ea65ad","slug":"agibot-go-1","name":"Genie Operator-1 (GO-1)","description":"AgiBot's universal embodied foundation model, Genie Operator-1 (GO-1), launched March 2025. Introduces the Vision-Language-Latent-Action (ViLLA) framework: a Vision-Language Model plus a Mixture-of-Experts (a Latent Planner trained on cross-embodiment and human-operation data, and an Action Expert trained on over a million real robot demonstrations). Supports learning from human video, few-shot generalization, cross-embodiment adaptation, and continuous self-evolution.","brainType":"foundation-model","isOpen":false,"maturityStage":"pilot","architecture":null,"reviewStatus":"reviewed","sources":[{"url":"https://www.globenewswire.com/news-release/2025/03/11/3040608/0/en/AgiBot-GO-1-The-Evolution-of-Generalist-Embodied-Foundation-Model-from-VLA-to-ViLLA.html","title":"AgiBot GO-1: the evolution of a generalist embodied foundation model from VLA to ViLLA (Mar 11, 2025)","sourceName":"AgiBot (GlobeNewswire)"},{"url":"https://www.barchart.com/story/news/31336659/agibot-unveils-universal-embodied-foundation-model-genie-operator-1-go-1","title":"AgiBot unveils its universal embodied foundation model Genie Operator-1 (GO-1)","sourceName":"Barchart"},{"url":"https://www.globenewswire.com/news-release/2025/03/10/3040128/0/en/AgiBot-GO-1-The-Evolution-of-Generalist-Embodied-Foundation-Model-from-VLA-to-ViLLA.html","date":"2025-03-10","title":"AgiBot GO-1: The Evolution of Generalist Embodied Foundation Model from VLA to ViLLA","sourceName":"AgiBot / GlobeNewswire"},{"url":"https://www.agibot.com.cn/article/189/detail/56.html","title":"AgiBot GO-1 ViLLA announcement","sourceName":"AgiBot"},{"url":"https://www.agibot.com/article/231/detail/56.html","title":"The unity of reasoning and action: AGIBOT unveils Genie Operator","sourceName":"AGIBOT"},{"url":"https://github.com/OpenDriveLab/AgiBot-World","title":"OpenDriveLab AgiBot-World","sourceName":"OpenDriveLab"}],"keyFacts":[{"label":"Model type","value":"Foundation model"},{"label":"Maturity stage","value":"Pilot"},{"label":"Open source","value":"No"},{"label":"Architecture","value":"Vision-Language-Latent-Action (ViLLA) framework with Vision-Language Model and Mixture-of-Experts (Latent Planner and Action Expert)"},{"label":"Training data","value":"Cross-embodiment and human-operation data plus over a million real robot demonstrations"},{"label":"GO-1 ViLLA foundation model","value":"AgiBot describes GO-1 (Genie Operator-1) as a generalist embodied foundation model that evolves from VLA to a Vision-Language-Latent-Action (ViLLA) stack for scene understanding and dexterous manipulation (AgiBot GO-1)."},{"label":"Chinese GO-1 product framing","value":"AgiBot's Chinese product materials present GO-1 as a general embodied base model for robot deployment workflows (AgiBot GO-1 detail)."},{"label":"Vision-language-latent-action model","value":"AGIBOT describes Genie Operator-1 as an embodied model that unifies vision, language, and action through a vision-language-latent-action framework (AGIBOT GO-1)."},{"label":"Open research release","value":"The OpenDriveLab AgiBot-World repository provides public code and datasets associated with AGIBOT's embodied-robotics research, including GO-1 workflows (AgiBot-World repository)."}],"aliases":["AgiBot GO-1"],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-05-30T15:14:26.123Z","updatedAt":"2026-10-10T01:23:40.505Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/agibot-go-1","url":"https://registry.deploy.report/brains/agibot-go-1","name":"Genie Operator-1 (GO-1)","alternateName":["AgiBot GO-1"],"description":"AgiBot's universal embodied foundation model, Genie Operator-1 (GO-1), launched March 2025. Introduces the Vision-Language-Latent-Action (ViLLA) framework: a Vision-Language Model plus a Mixture-of-Experts (a Latent Planner trained on cross-embodiment and human-operation data, and an Action Expert trained on over a million real robot demonstrations). Supports learning from human video, few-shot generalization, cross-embodiment adaptation, and continuous self-evolution.","identifier":"e26cbf32-1225-4222-ad6e-cbf986ea65ad","applicationCategory":"foundation-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"pilot","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":6,"primary_source_types":["code-repository","primary-company-ir"]}}}