rezaho/MARSYS
Multi-Agent Reasoning Systems
This is a framework for software developers to build sophisticated AI applications by orchestrating multiple specialized AI agents. Developers define the tasks, goals, and communication paths for each AI agent, which then collaborate to produce a final output, like a research summary. This allows developers to create complex, multi-step AI workflows that can handle long-running tasks and even include human oversight.
Available on PyPI.
Use this if you are a software developer building complex AI applications that require multiple AI models to collaborate on a task, or need to integrate human approval into AI workflows.
Not ideal if you are a business user looking for an out-of-the-box AI solution, or a developer simply needing a single AI model for a straightforward task.
Stars
13
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 28, 2026
Commits (30d)
0
Dependencies
24
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/rezaho/MARSYS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google-deepmind/concordia
A library for generative social simulation
Mai-xiyu/Minecraft_AI
AI Play Minecraft
mikelma/craftium
A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI...
cocacola-lab/MineLand
Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs
Dominien/brunnfeld-agentic-world
Medieval village economy simulation — up to 1000 LLM agents across multiple villages, driven by...