Simple self-hosted LLM assistant with user-steered compounding

I built a lightweight personal LLM assistant running on Cloudflare Workers + Durable Objects. The idea is simple: you pick a category and topic when starting a conversation, and the backend keeps a running summary per category/topic—so context compounds naturally across sessions without any RAG or embeddings overhead.

No agentic magic, no vector stores. Just a clean singleton Durable Object that maintains state, Workers AI as the default provider, and optional OpenRouter support for bigger models. It runs free on Cloudflare's free tier with the default setup.

I started this to learn Durable Objects and turn a rough idea into something usable. After losing my job recently, I spent more time refining it with friends' feedback—focusing on simplicity in deployment and daily use. This week I open-sourced it so others can try.

Repo: https://github.com/kol3x/pawmc

Details:

• $0 cost on Cloudflare free tier (default config)
• Everything in a singleton Durable Object
• Workers AI as the default provider
• OpenRouter support for stable access and larger models (paid tokens)