Someone here has been trying to run an icm shaped system on gemini bc IT wont hand out api keys, and hit the wall where gemini code assist in vs code forgets the instructions and only takes one md file, and a Gem holds ten docs but cant write back to itself. gemini cli is the piece that closes this. u sign in with a google account over oauth, no api key involved at all, and the free tier is 60 requests a minute and 1000 a day. the reason it matters for icm specifically is that it loads context files hierarchically, the same shape the methodology assumes. it reads ~/.gemini/GEMINI.md, then the GEMINI.md at ur project root, then ones sitting in subfolders, and merges them in that order. u can pull other markdown into a context file with @path/to/file.md, so ur tree stays a tree instead of one pasted blob. /memory show prints the combined context that actually loaded, which is how u verify it rather than hoping. /memory refresh re-scans after u edit. and it writes back to disk, which is the bit a Gem cant do. for sharing with the team it just becomes the repo. they clone it, they get the same context files, nobody is hand maintaining a Gem. one honest caveat, the free oauth tier is tied to a personal google account, so if ur work account is locked down u would be putting work context thru a personal login. worth clearing that with IT first instead of finding out later.

Hello smart people of the internet, Previously I asked about how you might use ICM without using Claude. There were some awesome answers, particularly about some closed/narrow options like copilot. I'm looking to utilize Gemini in the same manner where I can build/share a templated system with other people within the team. We are using the "walled garden" personal Gemini (pro license) which means that it's not easy to use outside of the Gemini . google .com portal. Access to API keys are off the table (thanks IT) so I cant use a limited free tier. So far I've tried - using Gemini code assistant via VS Code - I can connect, however it seems to immediately forget the instructions and constantly wants me to attach a MD file manually (and only one seems to be able to be added). - Use Gemini "Gem" which is kind of ok, but we're then looking at the near perfected product to then share. A gem allows context window to prefilled and up to 10 documents to be attached. It won't write back to itself so you will have to constant update it manually. Thanks for anyone providing suggestions or actual guides on how this might be achieved. Ideal outcome is not manually updating files.

I've been tinkering with a question. Some of the applications I'm building might use specialized agents deployed online. Think off a customer service agent. My whole process is built with ICM and that agent or agents have their whole structure, it works locally, they have their context, reference files, rules, all the good stuff. However, they live in my folders in my PC. And I know how to deployed apps online, I mean there's a whole bunch of examples here on how to do it. But how do I do that for agents? I know it is a play of the Claude API embedded into the website or whichever place I need it into. But how do I direct that API to work though my whole ICM architecture for that specific agent so it knows the right context? Example: Customer asks about product A, the agent knows through the context.md that all product A info is in Product A's folder so it needs to go there and read the relevant files. All that is great and works locally but how do I deploy it online?

I’m currently building a music sequencer for my brother Any musicians/builders here who have built something similar? Would love to compare ideas and learn from your experience.

I have a passion project that I am working toward: Neuroadaptive learning environment support by AI in Higher Learning so that Universities are inclusive by design and not by accommodation. Patent pending. I will need a senior engineer to collaborate with. I'm not sure how to go about vetting them.