zoe-yyx/AgentNet

[NIPS2025] A decentralized, RAG-enhanced multi-agent framework for LLMs with dynamic task routing and agent evolution.

24
/ 100
Experimental

This framework helps AI researchers and system architects build advanced AI systems where multiple large language models (LLMs) need to work together on complex tasks without a central boss. It takes individual LLMs and connects them into a smart, evolving network where each LLM learns and makes its own decisions. The output is a more robust and adaptable multi-agent AI system that can handle dynamic challenges.

No commits in the last 6 months.

Use this if you need to create fault-tolerant, adaptive AI systems where LLMs collaborate on evolving tasks, and you want to avoid single points of failure or rigid, predefined workflows.

Not ideal if your AI application requires a simple, static workflow with predictable tasks and a centralized control structure is acceptable.

AI-system-design multi-agent-AI LLM-orchestration decentralized-AI AI-research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 8 / 25

How are scores calculated?

Stars

36

Forks

3

Language

Python

License

Last pushed

Oct 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/zoe-yyx/AgentNet"

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