{"slug": "show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building", "title": "Show HN: Kuron – An LLM acts as your app so you can try ideas before building", "summary": "A developer released Kuron, an open-source tool that uses a large language model to act as a running application so users can test an idea before building it, with the LLM setting up the system and then executing every action rather than generating code per idea. In a recorded run on an M1 Max through Claude Code, Claude Sonnet 5.5 set up a small-clinic prototype from a one-line English idea in 65 seconds using 16 tool calls at a cost of about $0.41, with Claude Haiku 5.5 handling button presses. Kuron exposes generic tools over MCP — data storage, screen definition, notifications, camera, microphone, sound, speech, drawing and timers — and during setup the LLM estimates how a shippable version would perform each action, with error rates and delays such as 10% and 2.5 seconds for clinic check-in, which users can toggle from Ideal to Existing tech.", "body_md": "Write an idea in one line — even one that would take ~50 hours to build. Within about a minute it is running on minimal screens and you can use it by hand, so you can find out whether it is worth building. Nothing is generated per idea: the LLM sets the system up, then *is* the system on every action.\n\n```\none line ─▶ setup agent (LLM + tools) ─▶ brief · data · screens · timers · checks · reality estimate\n                                               │\nbutton / timer / camera / mic ─▶ event agent (LLM + tools) ─▶ reads what it needs, changes the world,\n                                               │               speaks, plays sound, draws\n\"this should…\" ─▶ request agent ─▶ changes its own brief, screens, data, checks\n                                               │\n                               world.json ◀────┘ ─▶ minimal face: website, phone, desktop, IoT panel, watch…\n```\n\nThe code is only a set of generic tools exposed over MCP — store and read data, define a screen, notify, look through the camera, listen to the mic, play and shape sound, speak, draw, set timers — plus a minimal renderer. Every tool checks the *shape* of its input and answers in words; the LLM corrects itself. There is no business logic, no word list, no per-idea exception in the code.\n\nWhen a prototype behaves wrongly, you don’t patch it: you tell it how it should behave (“urgent patients go first”), and the request agent rewrites its own brief, screens and checks.\n\nOne English idea file for a small clinic: reception tablet, doctor’s PC, stock PC, patient’s phone and waiting-room display. Claude set it up from the idea in **65 s with 16 tool calls (about $0.41)**, then acted as the system on every button. Each reply below is what it actually did; only the waiting time between steps is shortened.\n\nLoading the recorded run…\n\nRecorded on an M1 Max through Claude Code: Claude Sonnet 5.5 for setup and requests, Claude Haiku 5.5 for button presses. The screens are drawn by the same renderer the tool uses. The raw recording is [replay.json](replay.json).\n\nA prototype where the LLM does everything is dangerously convincing. So during setup the LLM also estimates, for every action, how a shippable version would do it — ordinary code, a model, an outside service, or not yet possible — with an error rate and a delay. Flip **Ideal → Existing tech** and the system behaves that way: late, sometimes wrong, sound leaking past the earphones.\n\n| Action (clinic, from the run above) | How a real version would do it | Errors | Delay | \n|---|---|---|---|\n| Check in |  | 10% | 2.5 s | \n| Send interview |  | 12% | 4.0 s | \n| Prescribe |  | 10% | 3.5 s | \n| To billing |  | 20% | 3.0 s | \n| Cancel booking |  | 3% | 0.3 s | \n\nAfter you have tried it, kuron turns what the system actually did into a spec — data, screens, golden examples taken from real tool calls, this table — and an implementation plan for a coding agent.\n\nUI and app generators (Lovable, v0, Figma Make…) build the screens and the code behind them, and prototypes usually fake the judgement with fixed data. kuron builds the *behaviour*: the face stays minimal, while the judgement, the data and the hand-offs between roles really happen.\n\n[Open kuron on claude.ai](https://claude.ai/artifact/UMMbf2FcV3ULi6d5WaW1yp). It starts with the clinic above already set up; press any button, ask for a change, flip to existing tech, or write your own idea. It runs on your own Claude account (you are asked once), so you need to be signed in to claude.ai. The browser version has no microphone and runs timers when you press them.\n\nNeeds Node.js 20+ and [Claude Code](https://claude.com/claude-code) (logged in). No npm dependencies.\n\n```\ngit clone https://github.com/Ag3497120/kuron\ncd kuron\nnode bin/kuron.js dev examples     # http://127.0.0.1:4870/\n```\n\nPick an example — a task list, an IoT fridge with a phone app, a sales deal desk, earphones that let only important sounds through — or press **+ New** and write your own idea in one line. Each example sets itself up the first time you open it (about a minute).\n\n`--preset local` runs everything on [Ollama](https://ollama.com) with tool calling instead of Claude. The tools are a plain MCP server, so any MCP client can drive the same system: `node bin/kuron.js hands --url http://127.0.0.1:4870`.", "url": "https://wpnews.pro/news/show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building", "canonical_source": "https://kuron.pages.dev/", "published_at": "2026-10-22 06:28:12+00:00", "updated_at": "2026-10-22 06:41:42.039315+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "agent-protocols", "ai-products"], "entities": ["Kuron", "Claude", "Claude Code", "Claude Sonnet 5.5", "Claude Haiku 5.5", "MCP", "Lovable", "v0"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building", "markdown": "https://wpnews.pro/news/show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building.md", "text": "https://wpnews.pro/news/show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building.txt", "jsonld": "https://wpnews.pro/news/show-hn-kuron-an-llm-acts-as-your-app-so-you-can-try-ideas-before-building.jsonld"}}