Show HN: We built an AI-agent with a state machine instead of a giant prompt
Hacker News - AI
Jul 4, 2025 11:15
chandralegend
1 views
hackernewsaidiscussion
Summary
A team developed NOMOS, an open-source engine that uses a step-based state machine to manage LLM agents, addressing the unpredictability and lack of testability found in prompt-based approaches. By making each state explicit and independently testable, NOMOS offers greater reliability, traceability, and ease of collaboration for enterprise AI workflows. This approach could set a new standard for building robust, maintainable AI agents in production environments.
Hi HN, Last year we tried to bring an LLM “agent” into a real enterprise workflow. It looked easy in the demo videos. In production it was… chaos. • Tiny wording tweaks = totally different behaviour • Impossible to unit-test; every run was a new adventure • One mega-prompt meant one engineer could break the whole thing • SOC-2 reviewers hated the “no traceability” story We wanted the predictability of a backend service and the flexibility of an LLM. So we built NOMOS: a step-based state-machine engine that wraps any LLM (OpenAI, Claude, local). Each state is explicit, testable, and independently ownable—think Git-friendly diff-able YAML. Open-source core (MIT), today. • GitHub: https://github.com/dowhile/nomos • Documentation: https://nomos.dowhile.dev Looking ahead: we’re also prototyping Kosmos, a “Vercel for AI agents” that can deploy NOMOS or other frameworks behind a single control plane. If that sounds useful, Join the waitlist for free paid membership for limited amount of peopl