Neptune – Give your coding agents DevOps superpowers
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…
In plain words
Neptune is an open-source MCP server that enables AI coding agents to deploy software to AWS, not just write code. It runs in the IDE, analyzes codebases using ASTs to generate a deterministic infrastructure specification called neptune.json, and lets developers inspect and approve every change before deployment. Built by the Shuttle team, Neptune keeps users in control by requiring approval at each step, allowing AI agents to actually ship applications safely.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, December 2025
the whole month →- GP
Life & fun · Dec 2025 · dosaygo-studio.github.io
- JG
Hi everyone! My name's Luke and I made the original Jmail here alongside Riley Walz. We had a ton of friends collaborate on building out more of the app suite last night in lieue of DOJ's "Epstein files" release. Please AMA!
Life & fun · Dec 2025 · jmail.world
PlanEat AI▲733AI turns your health goals into a 7-day menu & grocery list
AI · Dec 2025 · planeatai.com
- 2G
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo (https://github.com/DOSAYGO-STUDIO/HackerBook): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's…
Dev tools · Dec 2025 · hackerbook.dosaygo.com
