Interesting concept, I like it, and I have some experience working on a vaguely similar system (an AI agent manager for the company I worked for previously). One thing that I'm wondering, after reading your proposal, is how you intend to track off-chain influence? If people are driving opinion in a hidden or discrete manner, how does that get exposed to the memory system?
Viewing post in The Governance Memory System (GMS)
Thank you for your feedback! If you have some time, I'd like to pick your brain on some agent architecture decisions, if possible. Right now, off-chain influence will be limited to Telegram, Slack, and Discord chats. There's a tool called Telescope that asks people to consent to having what they've said documented. The KOI implementation I also mentioned can create knowledge objects for these threads and grouped statements; it should also track different reactions within chats, so it can assess how the statements were received.