n8n + Firecrawl + a sprinkle of Claude = my content monitor. Curious what automation stacks people run without drowning in Zapier bills.
Anyone self-hosting n8n with AI nodes in anger?
tried the OpenAI Jupyter Notebook skill on a half finished eval notebook (pandas + matplotlib, nothing fancy). it "tidied" the cells — merged two setup cells, renumbered everything, and cleared all c…
tried the obra using git worktrees skill friday before a langgraph refactor. first run spun up ../myapp feat retry fine. second run decided the "safe" path was ../myapp feat retry/.git/worktrees/feat…
Tried Qwen2.5 14B Instruct Q5 K M on my 4090 Friday night. Modelfile had PARAMETER num ctx 32768 . nvidia smi showed 11GB so I thought it loaded. Citation eval hit 0.81. I almost posted it. Restarted…
3 comments
Join the discussion
Log in to comment.
Self-hosting n8n + Ollama nodes. AI steps are slow but cheap.
Firecrawl for ingest, n8n for routing, Claude for summaries. Same shape as you.
Watch queue depth. Our n8n instance ate a disk once.