Brain
NVIDIA’s open world action model for robot manipulation, built on NVIDIA Cosmos. It predicts future video and robot actions together and runs on parallel grippers, dexterous hands and humanoids. A smaller GR00T 2 Turbo variant runs on the Unitree G1 humanoid’s own Jetson Thor.
Foundation model · Maturity: Pilot · Open source
Machine-readable surfaces
- Markdown mirror: /brains/gr00t-2.md
- RSS feed: /brains/gr00t-2/feed.xml
- JSON-LD: embedded in this page’s head
- REST API: /v1/brains/c9775d72-6fba-48b3-ade5-3355787d7f72
- Revision history: /brains/gr00t-2/history
- Data documentation: /data
- Query this programmatically: Deploy MCP
Key facts
Developed by (1)
Common questions
What is GR00T 2?
NVIDIA’s open world action model for robot manipulation, built on NVIDIA Cosmos. It predicts future video and robot actions together and runs on parallel grippers, dexterous hands and humanoids. A smaller GR00T 2 Turbo variant runs on the Unitree G1 humanoid’s own Jetson Thor.
Who developed GR00T 2?
Is GR00T 2 open source?
Yes. GR00T 2 is recorded as open-source / open-weights on the DEPLOY registry, meaning model weights or source code are publicly available.
What type of AI is GR00T 2?
GR00T 2 is a foundation model on the DEPLOY registry.
What is GR00T 2's maturity stage?
GR00T 2 is at the pilot stage on the DEPLOY maturity ladder. Pilot stage means at least one named-customer trial deployment is verified.
Which robots run on GR00T 2?
No robot models on the DEPLOY registry are recorded as running GR00T 2. DEPLOY wires brain-to-model connections only when the wiring is verifiable from primary sources; absence may reflect pre-deployment or unverified manufacturer claims.
Sources (2)
Methodology: Verified · 2 sources (no primary) · last reviewed 2026-11-09
Verification posture
Verified
Low confidence
Review state
Stable
Last reviewed 2026-11-09
Maturity + lifecycle
Maturity stage: pilot
Sources by quality tier
- 2
- unclassified
- Unclassified source
The framework is documented at /methodology. Corrections at /corrections. Reviewer: DEPLOY editorial team.
Methodology surface for GR00T 2.Canonical ID c9775d72-6fba-48b3-ade5-3355787d7f72