by CUTEPKQ · Agent Tool · ★ 143
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
NEWTON: Agentic Planning for Physically Grounded Video Generation
| Stars | 143 |
| Forks | 3 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 52.0310638192928/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-31 |
| Created | 2026-06-13 |
| Platforms | python |
| Est. Tokens | ~13k |
These tools work well together with NEWTON for enhanced workflows:
Looking for a NEWTON alternative? If you're comparing NEWTON with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A framework for agentic tool use training with reinforcement learning
Open-source robotics simulator for coding agents: HTTP/JSON + MCP control, Newton physics, wgpu rendering, ROS
Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.
OmniAgent (ICML 2026): the first native omni-modal agent for active video perception — a 7B agent that beats Q
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI l
Explore other popular agent tool tools:
NEWTON is NEWTON: Agentic Planning for Physically Grounded Video Generation. It is categorized as a Agent Tool with 143 GitHub stars.
NEWTON is primarily written in Python. It covers topics such as agentic-ai, agentic-video-generation, ai-agents.
You can find installation instructions and usage details in the NEWTON GitHub repository at github.com/CUTEPKQ/NEWTON. The project has 143 stars and 3 forks, indicating an active community.
NEWTON is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to NEWTON on Agent Skills Hub include ToolBrain, omnisim, Auto-Use. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: