this is actually a perfect use case, mostly deterministic workflows that need LLMs to fill in the gaps or do the knowledge work. As you mentioned, you can either add it as a row in a CSV file (sheets), use the baked-in memory block and treat it as simple storage, store the row in supabase, or use the knowledgebase. Basically, there are a ton of ways that this can be done that don't require you to maintain the memory solution yourself. you can even detect the updated and deleted items by keeping some sort of version-controlled snapshot of each row in the csv and updating it as you go.

I can't tell you whether it got better in n8n, but I can definitively say that this sounds like a great candidate workflow to build in sim :)

I really like windmill.dev which should support your scenario just fine

N8n can definitely do this.

They recently added native tables, albeit still just a few data types, you can store stuff in and use in workflows.

But does that require AI agents? Well, maybe the extraction step, if it's not CSV but a general-case web page.

Maybe in the middle, processing the items - classifying, summarizing.

But the post bills the tool as an n8n alternative. Therefore, I am evaluating it as such. Solid basics before the AI whizbang.

the agents would be great in the instructions where we need to `do something`, but asides from that is sounds like a pure orchestration task.

now, handling an integration to something like google sheets myself for a task this small is a nightmare, not to mention the separate table I'd need to keep to store the access token & refresh token and the permissions I'd need to get from google. on top of that, hosting it somewhere and then monitoring it.

Hey - could be a good use case for https://github.com/autokitteh/autokitteh - which gives you durable workflows over python. Since your logic is deterministic it's a simple python script that stores the history in memory, and autokitteh will take care of the persistancy aspect.