NAEOS

Specify once. Build anywhere

4 followers

Specify once. Build anywhere

4 followers

NAEOS is a declarative engineering platform that transforms specifications into high-quality software systems through a consistent, validated, and extensible pipeline.

Free

Launch tags:Software Engineering•Developer Tools•Artificial Intelligence

Launch Team / Built With

EneyProactive AI for Mac. Free test, 20,000 credits.

Promoted

Maker

📌

Hi Product Hunt! bayu here, the maker of NAEOS. I'm genuinely excited (and a little nervous) to share this one. The problem I kept hitting: every project starts with a great spec document, and six months later the spec and the code are strangers. Nobody maintains the spec because the code "is the source of truth." But then the code base grows, the docs rot, and every new engineer or AI assistant has to reverse-engineer the whole system. The idea: flip it. Make the specification the source of truth, and make the tooling so good that keeping the spec accurate is the path of least resistance. That's NAEOS — you describe your system once, and it parses, validates, builds an internal engineering model (NEIR), and generates real code in Go, TypeScript, Python, Java, and Rust. Not a scaffold — a consistent, validated, auditable pipeline. What's in v3.0.0 (the version we're launching with): Pipeline profiling, memory analysis, and stage caching — rebuilds reuse cached results A NEIR-aware LSP server with autocomplete, diagnostics, and go-to-definition for .naeos.yaml Distributed builds with naeos build --distributed --workers N VS Code extension generation with naeos dx vscode-gen Official example plugins and a microservices Go starter template The AI angle: we ship a compiler that turns the engineering model into instruction sets for 6 AI tools (Copilot, Claude Code, Cursor, Gemini CLI, Codex, OpenCode), plus an MCP server — so AI assistants work from an accurate model of your system instead of guessing. Try it in 30 seconds: curl -fsSL https://naeos.dev/install.sh | sh naeos create my-app naeos run --input-file spec.yaml It's open source (Apache 2.0) — the whole roadmap is public. I'd love feedback on what's missing, what's over-engineered, and what spec-driven workflow you'd want us to tackle next. Ask me anything — I'll be here all day.

Report

2mo ago

Forum Threads

p/naeos

•

1mo ago

Why are AI coding agents still hard to use in real engineering?

I ve been building NAEOS around a question:

What happens when AI coding agents move from write some code to actually participating in software engineering?

Most AI coding tools are getting very good at generating code.

But production engineering involves much more:

p/naeos

•

2mo ago

Why did we build NAEOS?

AI coding agents are getting incredibly good at writing code.

But while building with them, we kept seeing the same problem:

The agent knows how to code, but doesn't always know how the system should be engineered.

Architecture decisions, security rules, testing standards, project conventions, and engineering context are often scattered across repositories, docs, and people's heads.

p/naeos

•

2mo ago

Product Hunt Pre-Launch Thread 🚀

1/ We re getting ready to launch NAEOS on Product Hunt.

NAEOS is an AI Engineering Operating System for building production-ready software with AI coding agents.

Not another AI coding assistant.

We re building the engineering foundation around the agents.

View all