OpenAgentSkill Registry Manifest
Skill: VectorizedMultiAgentSimulator
Slug: proroklab-vectorizedmultiagentsimulator
Category: agent-frameworks
Description: VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.

Agent fit:
- Decision: 96/100 Production-ready
- Primary fit: RAG and knowledge
- Role: Primary pick

Supply profile:
- Track: Coding and developer agents
- Scenario: GitHub automation
- Applicable agents: Claude Code, CLI, Codex, Cursor, Python
- Maintenance: 28d since push
- Risk: Safe to try

Trust:
- Trust score: 88/100 Production candidate
- Audit: 89/100 Safe to try

Attribution:
- Status: Community indexed
- Source: GitHub star discovery
- Creator: proroklab
- Claim URL: https://www.openagentskill.com/skills/proroklab-vectorizedmultiagentsimulator#claim-this-skill

Install:
npx skills add proroklab/VectorizedMultiAgentSimulator

URLs:
- Web: https://www.openagentskill.com/skills/proroklab-vectorizedmultiagentsimulator
- API: https://www.openagentskill.com/api/agent/skills/proroklab-vectorizedmultiagentsimulator
- Install API: https://www.openagentskill.com/api/skills/proroklab-vectorizedmultiagentsimulator/install
- Repository: https://github.com/proroklab/VectorizedMultiAgentSimulator