Robot AI model
Genie Envisioner 1.0
Genie Envisioner combines a video world model with GE-Act action prediction, demonstrated on AgiBot G1, dual Franka and Agilex platforms. The license field covers GE-Base's inherited LTX-Video 0.9 RAIL-M License; repository code uses CC BY-NC-SA 4.0 with Apache-2.0 exceptions.
Records last verified Oct 13, 2026 · Send a correction
Also known as GE, GE-Base, GE-Act, GE-Sim
- Type
- World model
- Released / introduced
- Aug 7, 2025
- Public weights
- Public weights
- Licence / scope
- RAIL-M License
- Parameters
- Not disclosed
- Base model
- LTX-Video 2B (original GE-Base)
- Humanoid association
- Humanoid demonstrated
- Inputs
- vision, language
- Outputs
- predicted multi-view video, robot actions through GE-Act
Release dates can mark an announcement or paper introduction. Public checkpoints, code licences and weight terms are distinct; follow the publisher’s links for the stated scope.
Documented embodiments
Source-associated hardware; this list does not establish plug-and-play compatibility or commercial robot capability.
- AgiBot G1 →
Real manipulation is demonstrated with the GE-Act extension, not with the video predictor alone.
- Dual Franka
Cross-embodiment adaptation of GE-Act.
- Agilex Cobot Magic
Cross-embodiment adaptation of GE-Act.
Disclosed training data
More robot AI models
Evidence
Sources
- [s1] Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation ↗
Genie Envisioner research team · paper · published Aug 7, 2025 · accessed Oct 13, 2026
- [s2] Genie Envisioner paper: GE-Base, training data and GE-Act robot experiments ↗
Genie Envisioner research team · paper · published Oct 17, 2025 · accessed Oct 13, 2026
- [s3] Genie Envisioner 1.0 checkpoint card and weight-license scope ↗
AgiBot World team · official · accessed Oct 13, 2026
- [s4] LTX Video 0.9 RAIL-M License ↗
Lightricks · official · accessed Oct 13, 2026
- [s5] Genie Envisioner official repository: code exceptions and CC BY-NC-SA terms ↗
AgiBot · official · accessed Oct 13, 2026