🏘️ What happens when AI agents get their own goals, memories, and a town to live in?

Developer @aijoey built Whisper Town, a local multi-agent virtual town where 8 AI residents set their own goals, make decisions, and learn from what happens around them.

🧠 MiniCPM5-2B handles agent decision-making and action selection, while Qwen 27B turns their thoughts into dialogue and executable behaviors.

✨ Highlights: 🤖 8 autonomous AI residents with independent long-term memory 🧩 Agents can start projects, collaborate, share information, or walk away 🔄 Residents learn from failures and adapt their future decisions 💾 7,000+ memories accumulated through ongoing interactions ⚡ Fully local inference running on two NVIDIA DGX Spark systems

A great example of what developers can build with MiniCPM5-2B. ⚡

🔗 Explore Whisper Town: http://whispertown.vercel.app/ 🤗 Model: http://huggingface.co/openbmb/MiniCPM5-2B

Give MiniCPM5-2B a try and build your own agentic applications! 🚀