Show HN: Neptune – Give your coding agents DevOps superpowers

Posted by nodar-d 1 day ago

Hi HN,

We are the team behind Shuttle (YC S20). We just shipped Neptune, (https://github.com/shuttle-hq/neptune-mcp) an open source MCP server that lets coding agents actually deploy software, not just write code. Behind it is an app deployment platform we built to be friendly for AI agents.

Neptune runs in your IDE. It reads your codebase, analyzes its structure and intent using ASTs and inference, and generates a deterministic infrastructure spec called neptune.json. You can inspect every change, approve it, and apply it. Think: coding agents that can actually ship safely to AWS.

How it works in practice:

1. Take any of your existing apps 2. Install Neptune mcp & login 3. Tell your agent to deploy 4. Watch it do everything else for you and (super important) it keeps you in the loop at every step, asking for your approval and guidance. We’ve spent most of our time implementing guardrails to make this as safe as if you were doing it yourself.

We built this after seeing teams rely on AI to write services, but still hand-craft Terraform and YAML. The AI could write code, but it could not understand the system around it. Neptune tries to close that gap.

Right now we have support for the most basic AWS products (ECS, S3, SecretManager), and we support postgres (thanks to Neon) and we are adding more resources as we speak. For now, your apps are all deployed to our a shared tenancy AWS account, and “bring your own cloud” account is coming soon too.

If you are also excited about a future where coding agents can help you reliably ship stuff into production, try it and share what you think.

If you have tried it on shared tenancy and would like to run it in your own AWS account, just get in touch and we’d be happy to help.

Comments

Comment by jvcor13 1 day ago

This looks interesting - will I be able to bring my own cloud?

Comment by nodar-d 1 day ago

hey, yes - right now it's only deployable to our AWS shared tenancy account, but we're working on bring your own cloud and long-term we see most serious users to go towards that setup. if you're interested in plugging this into your aws account - get in touch with me here nodar@neptune.dev

Comment by nzdevhacker 1 day ago

I don't fully get this - can't I just use AI to write terraform for me?

Comment by nodar-d 1 day ago

Short answer: you can, but it breaks down fast.

LLMs are decent at writing Terraform, but Terraform wasn’t designed for agents. A tiny app change often explodes into hundreds of lines of diff across modules, IAM, networking, state.

> use AI to write terraform for me

The real problem isn’t generating config, it’s control. With vibecoded Terraform you get: * no guardrails on what can change * hard to review whether a diff is safe * easy to accidentally destroy or over-permission infra * state + implicit dependencies are brittle for autonomous edits

We built Neptune to solve those issues and eliminate as many footguns as possible. We are spending a lot of our time thinking about guardrails so you can deploy code with AI safely

Comment by JojoFatsani 1 day ago

I write make Terraform PR’s with Cursor daily. The Terraform Registry is easy for the agent to comprehend, HCL has been stable for years now. Good terraform linters and plugins exist. and you can pretty easily tell your agent to run and analyze terraform plans without applying.

If Cursor/CC can’t be trusted with my TF code base why should I trust your tool? The same guardrails are needed for any of those not to mention the pesky meat-based code contributors.