1/ What people call multi-agent systems are really single agent, since the same LLM & codebase are used. Here's Yohei (creator of BabyAGI) making that case in a recent thread.

1/ What people call multi-agent systems are really single agent, since the same LLM & codebase are used. Here's Yohei (creator of BabyAGI) making that case in a recent thread. https://x.com/yoheinakajima/status/1781183534998380576?t=L-jW1X_x9JBbaO9eCiczQA&s=19

2/ So we implemented BabyAGI as a **true** multi-agent system for the first time. Watch our demo showing BabyAGI running with the agents on different nodes.

Decentralized AI Workflow & Agent Orchestration Platform | Enabling a New Paradigm of Software

2/ So we implemented BabyAGI as a **true** multi-agent system for the first time. Watch our demo showing BabyAGI running with the agents on different nodes. https://www.youtube.com/watch?v=nzV04zOA0f0

3/ We're working on building out more examples of true multi-agent systems including Stanford generative agents and MetaGPT. If have an app that you want to build, check out our SDK and get in touch!

3/ We're working on building out more examples of true multi-agent systems including Stanford generative agents and MetaGPT. If have an app that you want to build, check out our SDK and get in touch! https://github.com/NapthaAI/naptha-sdk