SalesforceAIResearch/MAS-Zero

Designing Multi-Agent Systems with Zero Supervision

40
/ 100
Emerging

This project helps AI researchers and developers design complex AI systems involving multiple interacting agents, without needing extensive pre-labeled data or human oversight. You provide a high-level task, and it generates the optimal multi-agent system (MAS) code, which is then evaluated for solvability and completeness. The output is a verified, efficient MAS design ready for implementation.

115 stars. No commits in the last 6 months.

Use this if you are an AI researcher or developer building sophisticated multi-agent AI systems and want to automate the design process with minimal manual supervision.

Not ideal if you are looking for a plug-and-play solution for simple, single-agent tasks or if you are not comfortable working with code generation and evaluation.

AI-system-design multi-agent-AI autonomous-system-development AI-research code-generation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

115

Forks

12

Language

Python

License

Apache-2.0

Last pushed

Jul 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/SalesforceAIResearch/MAS-Zero"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.