Trying to work out the best way to run the Karpathy like LLM wiki for a team, not just solo, and want to see how people are actually doing it. Solo is relatively simple: raw folder in, Claude builds a linked wiki out, plus an index and a log. No vector DB, just markdown. Where it gets interesting is a team, say five people in a sales operation all feeding and querying the same brain. How are you handling the shared vault? One person owning the ingest to keep the structure clean, or everyone in at once? Git repo, Obsidian Sync, something else? Keen to hear what's actually holding up in practice. Thanks

When deploying an ICM folder structure to an actual client, asking them to drop it into their claude seems reasonable for us techy people, but some of my clients are not technical enough to even do that. What other options are people using? I'm a traditional web app guy, so deploying a cloudflare worker with some backend code and a database etc is what I would traditionally try and do. That model is not as clear cut as a winner as it used to be! Is it time to look at agentic systems to be able to deploy ICM so my clients can actually use it in their day to day? Or do we simply train them up to use claude? Or is there something else that people are doing?

I'm curious has anyone adapted or adopted this framework to work with any of the other Frontier models like Gemini, ChatGPT, Grok etc. If so what does this adaption look like? what did you do to make this work without having to recreate everything? I see a future where my root folder has a Claude.md, a Gemini.md etc and when i use that LLM and my folder structure it just works.....

I've been working on a cold email builder skill that runs in CoWork. So if you're prospecting right now, or writing cold emails, this one's for you. Two things it does: Paste a cold email you're already sending and it scores it, tells you why it's landing or not Or it builds you one from scratch. The bit I actually care about: it's not a random AI generator. - Every rule in it is built on real data, peer-reviewed studies, the actual Gmail and Outlook rulebooks, vendor sets in the tens of millions of emails. - Weighted by what's proven, not what sounds clever. Have a look and let me know what you think... this is one of the modules I just created in a wider project - "Bingley" an AI sales assistant.

Hey guys, I'm trying to figure out if Obsidian is worth adding to my stack. Been seeing it everywhere for a while now, everyone's using it as memory for Claude, which makes sense, it's just markdown folders. Thing is, I feel like I've already got my own version: one HQ folder of markdown files Claude reads at the start of every session, memory file, context file per project. Curious what you guys are doing. Anyone running Obsidian over an already decent folder setup? Any value add I'm missing? Cheers