Python · MIT
CUTEPKQ/NEWTON
NEWTON: Agentic Planning for Physically Grounded Video Generation
★ 139
Stars
3 forks · 1 open issues
flat
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
13.1
Momentum / 100
see the breakdown below
4mo ago
Created
last push 3mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | flat, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 6.9 | last push 3mo ago; decays to zero at 180 days |
| Scale | 15 | 6.2 | 139 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 13.1 | sum of the above |
Detail
| Topics | agentic-aiagentic-video-generationai-agentsaigccomputer-visiondiffusion-modelsgrpollm-agentmultimodalphysics-simulationreinforcement-learningresearch-papertext-to-videotool-usevideo-diffusionvideo-generationvision-language-modelworld-model |
| Matched on | AI Agents (llm-agent) Computer Vision (computer-vision) |
| Short window | +0 stars over 7 days = 0.0/day |
| Long window | +-3 stars over 26 days = -0.1/day |
| Lifetime average | 0.96 stars/day over 145 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |