Show HN: Pawmc a.k.a. talking diary, an LLM chat with compartmentalised memory

Developer kol3x released Pawmc, an open-source LLM chat app that keeps context in isolated memory buckets called "diaries" and "topics," so a conversation started in { diary: personal, topic: books } receives the first message plus summaries of that diary and topic. Pawmc uses a minimal system prompt and deliberately omits tools and web search, treating the conversations themselves as the source of truth and the topic and diary summaries as a lightweight wiki, a simpler take on Andrej Karpathy's LLM Wiki concept. The project, posted to Hacker News as "Pawmc a.k.a. talking diary," includes a hosted demo with a scripted walkthrough that runs without an LLM and a repository at github.com/kol3x/pawmc.

What pawmc is from the blog post : It’s an LLM chat app with minimal system prompt and no tools/web-search by design. It stores most important context across your conversations in isolated buckets, called “diaries” and “topics”. This means that when you start a conversation in { diary: personal, topic: books }, the AI receives your first message along with summaries of that diary and that topic. It’s close in concept to Karpathy’s LLM Wiki, but simpler, easier to wrap your head around and maintain — no extra tooling and no different types of documents: it’s just your conversations as the source of truth and the summaries of topics and diaries as the “wiki” Post links a hosted demo with a scripted walkthrough of a typical flow, no LLM. And here is the repo: https://github.com/kol3x/pawmc https://github.com/kol3x/pawmc Comments URL: https://news.ycombinator.com/item?id=50183227 https://news.ycombinator.com/item?id=50183227 Points: 1 Comments: 0