I think everyone needs to fight to keep standards around AI tooling open, even if proprietary models are inevitable given the investment they take. AGENTS.md is a good example. Every Claude integration (Github CI etc), every shared artifact your boss comes to rely on entrenches us further. I think where possible all AI outputs need to be persisted in your own systems For example rather than have Claude create an artifact, have it create an HTML app / report in a repository you control. Make your own tools if you have to. I'm working on building a Formal Verification system for reviewing agent output into my notes / project management tool https://app.etherpk.com based on local markdown graphs for example.
Hey totally agreed, having a system external to the LLM ecosystem already helps with being able to coordinate data between chats, different LLMs, etc, and it will likely be increasingly important as you say in maintaining control over your data in an age of increasingly more capable AI that tends towards keeping your data in formats that are platform biased by default like artifacts in Claude.
Also minor bit of feedback, on your webpage you use the term PKMS. I'm guessing it means Personal Knowledge Management System, but it could be helpful to define it in parentheses or explicitly.
Otherwise, the app looks interesting. I'm probably not the target segment as nowadays I'm building out a lot of my own custom systems that I find myself using day to day to have granular control of the system to make it super customized, but I could see it being interesting to people who currently use miro/obsidian/notion/etc.
It requires a LOT more effort, but all of my tooling is non-agentic and fully model independent. If necessary, I can swap it all out to local or private cloud services.
It results in a far more involved development process, which helps keep me in the loop but also has a big speed impact.
Not handing it all off to agents can trigger some FOMO. I'm not sure how long I can keep it up and still compete.