The Autonomous Stack | 4 Claude agents. 6 months in production. Everything packaged

Hey Product Hunt, For the last 6 months, I have been running 4 autonomous cloud agents in production. I gave them the bankroll, the rules and a terminal. I’ve seen them waste money, make rules, and sometimes succeed. I built a lot of infrastructure to keep them alive and aligned. Today, I’m packaging all of this into The Autonomous Stack. This is not a structure. This is a reference architecture. You get 9 modules and about 40 files: – Canonical prompts for 4 agent archetypes (Shop Agent, Survival Trader, Neutral Trader, Janitor) – macOS launch plists for 2-hour, nightly, and weekly wake cycles – Postgres + Next.js approval-inbox for when agents need human permission – The exact scoreboard template I use to publicly report their failures. I use this to log – alignment-scan method to capture prompt-framing deviations. It costs $199 one time. You get the code, deployment guide, cost-control patterns, and errors appendix. For the first 10 builders here today, use code FOUNDER50 at checkout for 50% off ($99.50): https://buy.stripe.com/7sY6oIgCi… I’ll be here all day answering questions about agent infrastructure, quick alignment, and why you shouldn’t let the cloud keep your Stripe API keys. – David



<a href

Leave a Comment