Remy, an AI agent that compiles annotated Markdown into full-stack apps
Hi HN! Sean from MindStudio here. I wanted to share something we've been working on that I think introduces some new ideas into the "AI coding agent" space. Remy is an AI agent that builds full-stack TypeScript apps from a spec written in a new flavor of annotated markdown. The spec has two layers: prose describing what the app does, and annotations that carry the technical precision (data types, edge cases, validation rules, code snippets). The agent then "compiles" this into code: backend methods, typed schemas, frontends, test scenarios, and everything else are derived artifacts of the…
What it does
In the maker’s words, at launch
Hi HN! Sean from MindStudio here. I wanted to share something we've been working on that I think introduces some new ideas into the "AI coding agent" space. Remy is an AI agent that builds full-stack TypeScript apps from a spec written in a new flavor of annotated markdown. The spec has two layers: prose describing what the app does, and annotations that carry the technical precision (data types, edge cases, validation rules, code snippets). The agent then "compiles" this into code: backend methods, typed schemas, frontends, test scenarios, and everything else are derived artifacts of the spec. The idea is that this isn't no-code, and it isn't a shortcut for people who can't code. It's a step toward a new kind of higher-level programming language, one that happens to look like annotated prose instead of syntax with semicolons. The spec isn't a requirements document that generates code. It is the program. Code is compiled output, the same way nobody writes assembly by hand anymore but it's still running underneath. The spec and code stay in sync bidirectionally, and the same spec compiles into different interfaces (web app, REST API, conversational AI agent, MCP server, etc.) depending on what you need. We're obviously stretching the word "compile" here - the same spec isn't going to produce character-identical code each run. But we think it's an interesting mental model for thinking about where software is headed, and we think the gap between "functionally equivalent" and "effectively deterministic" is only going to continue narrowing with each generation of model. At their core, the apps Remy builds are git repos and markdown files, but we've also built a browser-based sandbox around them - editor, live preview, terminal, chat, and all the other bells and whistles - with managed infrastructure underneath: SQLite with automatic schema migrations, auth primitives (sms/email verification codes, sessions - you build your own UI and define your own user table), 200+ AI models and 1000+ integrations as SDK calls, deploy-on-push. Standard TypeScript, any npm package, any frontend framework. It's been really fun to see what is possible with all of these pieces connected. We're opening up in public alpha this morning. You can watch some demo videos, see some more details, and sign up to try it at: https://remy.msagent.ai (sign up for a free MindStudio account and then use "showhn" as the code to join the alpha without needing a paid account) There are also some more demo videos on YouTube: https://www.youtube.com/watch?v=2QJvBcAqQqA&list=PL1gRZlpf9_... As well as a tour of the interface: https://www.youtube.com/watch?v=ar724yPXgwU Would love to know what you think. Feel free to drop me an email at sean at mindstudio.ai too
Does the same job
all alternatives →- NONous – Open-Source Agent Framework with Autonomous, SWE Agents, WebUI2024 · github.com · ▲155
Hello HN! The day has finally come to stop adding features and start sharing what I've been building the last 5-6 months. It's a bit of CrewAI, OpenDevon, LangFuse/Cloud all in one, providing devs who prefer TypeScript an integrated framework thats provides a lot out of the box to start experimenting and building agents with. It started after peeking at the LangChain docs a few times and never liking the example code. I began experimenting with automating a simple Jira request from the engineering team to add an index to one of our Google Spanner databases (for context I'm the…
- ABA better way to handoff web bugs to AI agentsNov 2025 · github.com · ▲5
Hi HN, Zidan here. I’ve been experimenting with AI-assisted debugging and noticed a recurring gap: most tools optimize for agent-led exploration (ex: giving claude code a browser to click around and try to reproduce an issue). But in many cases, I've already found the bug myself. What I actually want is a way to hand the agent the exact context I just saw - without retyping steps, copying logs, or hoping it can reproduce the behavior. So we built FlowLens, an open-source MCP server + Chrome extension that captures browser context and lets coding agents inspect it as structured, queryable…
- ARAgents, run any coding agent on your subscription not API costsMay 2026 · agents-cli.sh · ▲6
Hi HN. I'm the founder of Phoenix Labs (ex TikTok, Applied AI) and we're open sourcing our internal tooling today which is like a toolchain / meta-harness for CLI agents useful for really scaling eng and creative work. We are a very small team who's building a very ambitious product so we had to find ways to squeeze every ounce of efficiency that we could get our hands on. Harness strengths of different models (Claude, GPTs) and CLI-harnesses (Claude Code, Codex), safe/robust browser integration to speed up UX/QA testing, teams cli to speed up security reviews and parallelize…
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 · 17d 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, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app