claudeers.
// MCP Servers

kuron

Claude (or any LLM) acts as the whole app instead of writing it: try an idea by hand in minutes, then turn it into a spec and a build plan.

// MCP Servers[ cli ][ api ][ desktop ][ web ][ mobile ][ claude ]#claude#ai-agents#anthropic#claude-code#llm#mcp#no-code#ollama#mcp-servers◷ MIT$open-sourceupdated 6 days ago

Install with your AI

Paste into Claude Code, Cursor, or any agent — it reads the repo and wires the tool into your project.

Install and set up kuron (git-clone project) into my current project.
Found on https://claudeers.com/kuron
Repo: https://github.com/Ag3497120/kuron
Homepage/docs: https://claude.ai/artifact/UMMbf2FcV3ULi6d5WaW1yp
Detected install method: git-clone → git clone https://github.com/Ag3497120/kuron
Category: mcp-servers. Platforms: cli, api, desktop, web, mobile.
Read the repo's README for exact setup and env vars, then install it and wire it into my project.

Claudeers Health Verdict:
unknown; community-verified: false. Confirm the source before running anything.
// or clone
git clone https://github.com/Ag3497120/kuron

// compatibility

Platformscli, api, desktop, web, mobile
Operating systems—
AI compatibilityclaude
LicenseMIT
Pricingopen-source
LanguageJavaScript

Get your FREE $2.50 API credits to access TickAtlas financial data ↗

kuron

Claude acts as the whole app instead of writing it.
Write an idea, use it by hand within minutes, and when you like it, get a build plan and the prompts to make it for real.

English · 日本語 · 中文

Six app ideas pasted at once: a greenhouse, a food truck, a Mars base, earphones, a wildfire watch and warehouse robots, each running as a whole system

Six ideas pasted at once, each running as a whole system. ▶ Watch the 2-minute video · A recorded run with every tool call

▶ Open kuron in your browser

No install. It runs on your own claude.ai account.


Why

I'm a student and a solo developer. AI already makes prototypes many times faster to build, but picturing ideas and market needs only in your head or in a plan is hard for one person. A mockup doesn't help much: the screens are the easy part, and what decides whether an idea is useful is the behaviour behind them.

So kuron reverses the order. Try the idea first, with something that really works, then build it. The name comes from the Japanese word 空論 (kūron), "armchair theory".

How it works

  1. Write the idea in plain words, in any language. One line is enough; a page is fine.
  2. Use it. Claude sets up minimal screens for each device or role, then plays everything that normally takes longest to build: the backend, the data and the wiring between screens. Every button press is handled by Claude acting as the system. No app code is generated.
  3. Reverse it. When you like what you see, kuron writes a spec from what the system actually did, a schedule, and the prompts to give a coding agent to build the same thing. For the clinic in the Japanese video, that came to about 92 hours.
idea ─▶ setup (LLM + tools) ─▶ brief · data · screens · timers · checks · existing-tech estimate
                                        │
button / timer / picture / sound ─▶ the LLM acts as the system ─▶ reads what it needs, changes the shared world
                                        │
"this should…" ─▶ the LLM changes its own screens, data and brief
                                        │
                        world.json ◀────┘ ─▶ minimal screens: website, phone, desktop, IoT panel, watch, terminal…

What's inside

  • Many devices, one world. A reception tablet, a doctor's PC, a patient's phone and a waiting-room board all show the same data, so one action shows up everywhere.
  • Change it in words. "Show why each patient got their urgency" — Claude rewrites its own screens and behaviour.
  • Existing tech switch. An LLM makes every idea look easy. Claude estimates, for each action, what a version you could ship today would use (plain code, a model, an outside service, or not possible yet), how often it would be wrong and how slow it would be, and the prototype then behaves that way.
  • Checks. Scenarios of a person using the system, played on a copy of it and judged.
  • Reverse. A spec with what the system actually did as golden examples, a schedule, and prompts for a coding agent.
  • Real-world parts. Test sounds, sound shaping for earphones, speech, drawings, pictures.
  • Faces beyond forms. The LLM chooses what the idea looks like: ordinary parts, a page in its own HTML and CSS, a drawing whose pieces can be touched, dragged or pressed by keys, or a stage — bodies and reflexes it declares, run every frame on your device, which tell it only what matters (a level cleared, a pose to judge).
  • Look ahead (off by default). While nobody is pressing anything, the LLM plays what can be pressed next on copies of the world; a press whose answer is ready takes it at once. It uses the LLM more.

Where it fits

UI / app generators (Lovable, v0, Figma Make…)kuron
What you getScreens and application codeMinimal screens; the LLM performs the behaviour live
Judgement and back-end logicMust be coded; prototypes usually fake itThe LLM actually decides (triage, recommendations, routing, estimates)
Technology that does not exist yetNothing works until it is connectedThe LLM plays that part
Several roles and devicesBuilt screen by screenThey share one world
Changing itEdit the codeSay "this should…"
Can it really be built?You find out by building itEvery action is estimated, and the switch lets you feel it
What you take awayThe codeA spec, golden examples and a build plan with prompts

Not a good fit: production use (an action takes several seconds and a few cents, and results vary slightly), pixel-level UI design, anything real-time like games, bulk exact data processing.

Run it on your machine

npx github:Ag3497120/kuron try

This copies the examples into ./kuron-examples and opens http://127.0.0.1:4870/. You need Node.js 20+ and one of: a logged-in Claude Code, an API key from a provider below, or Ollama.

Model nameRuns onNeeds
claude-… (default)Claude Code (claude -p, tools as an MCP server)a logged-in Claude Code
codex:<model>The Codex CLI (codex exec, with the tools passed as an MCP server)A logged-in Codex CLI
anthropic:<model>Anthropic APIANTHROPIC_API_KEY
openai:<model>OpenAI, or any compatible server via KURON_OPENAI_BASE_URLOPENAI_API_KEY
gemini: · openrouter: · groq:<model>that provider's OpenAI-compatible APIGEMINI_API_KEY · OPENROUTER_API_KEY · GROQ_API_KEY
lmstudio:<model>LM Studio on this machinenothing
anything elseOllama on this machineOllama

In the dev UI, the model names in the top bar open a picker: the model for setup and the model for button presses can each be changed to any of the above while the system runs.

kuron try --preset anthropic                                       # Anthropic API
kuron try --compile-model openai:<model> --cpu-model openai:<small> # any provider
kuron dev .                    # every .kuron idea in a folder; "+ New" from one line
kuron new "a clinic that …"    # write an idea and set it up
kuron check idea.kuron         # play the system's checks
kuron hands --url <host>       # the tools as an MCP server, for any MCP client

Browser version vs local: the browser version needs nothing but a claude.ai login; it has no microphone and runs timers when you press them. Its source is in web/ (node tools/build-web.mjs).

The line

Code containsCode never contains
Generic tools (store and read data, define screens, notify, sound, speech, drawings, pages, stages, timers, checks, estimates), a shape check on every tool call that answers in words, a renderer that shows what the LLM wrote and runs the reflexes it declaredBusiness judgement, word lists, guessing what the LLM meant, exceptions for one idea

When something does not fit, a tool tells the LLM what is wrong and the LLM corrects itself. When a prototype behaves wrongly, you tell it how it should behave. See docs/DESIGN.md.

Share an idea

kuron needs more ideas to be tested on, especially ones that break it. Add yours as examples/<name>.kuron in a pull request, or open an issue with what worked and what broke (the browser version's Feedback button does that for you). See CONTRIBUTING.md.

License

MIT

// faq

What is kuron?

Claude (or any LLM) acts as the whole app instead of writing it: try an idea by hand in minutes, then turn it into a spec and a build plan.. It is open-source on GitHub.

Is kuron free to use?

kuron is open-source under the MIT license, so it is free to use.

What category does kuron belong to?

kuron is listed under mcp-servers in the Claudeers registry of Claude-compatible tools.

10 views
★ 10 stars
unclaimed
updated 6 days ago

// embed badge

kuron on Claudeers
[![Claudeers](https://claudeers.com/api/badge/kuron.svg)](https://claudeers.com/kuron)

// retro hit counter

kuron hit counter
[![Hits](https://claudeers.com/api/counter/kuron.svg)](https://claudeers.com/kuron)

// reviews

// guestbook

0/500

// related in MCP Servers

🔓

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete…

// mcp-serversf/⟨HTML⟩★ 175,627◷ NOASSERTION[ claude ]
🔓

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io

// mcp-serversfarion1231/⟨Rust⟩★ 151,540◷ MIT[ claude ]
🔓

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

// mcp-serversJuliusBrussee/⟨JavaScript⟩★ 117,780◷ MIT[ claude ]
🔓

An open-source AI agent that brings the power of Gemini directly into your terminal.

// mcp-serversgoogle-gemini/⟨TypeScript⟩★ 108,744◷ Apache-2.0[ claude ]
→ see how kuron connects across the ecosystem