Livecodes logo

Livecodes

OrganizationPopular
live-codes
livecodes

Open-source, client-side code playground supporting 90+ languages/frameworks. Runs entirely in the browser with SDK for embedding. Entry point for all LiveCodes skills.

Overview

Publisherlive-codes
Repositorylivecodes
Skill namelivecodes
Stars
1.5K
Forks
271
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by live-codes on GitHub. Read the source before you install it.

Installation

Install the Livecodes AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/live-codes/livecodes/tree/develop/.agents/skills/livecodes
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/live-codes/livecodes.git /tmp/livecodes
mkdir -p .claude/skills
cp -r /tmp/livecodes/.agents/skills/livecodes .claude/skills/livecodes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Livecodes in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Livecodes on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Livecodes is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

LiveCodes Overview

LiveCodes is a feature-rich, open-source, client-side code playground that runs entirely in the browser. No server required. Supports 90+ languages/frameworks with a powerful SDK for embedding in any web application.

CRITICAL: LiveCodes runs CLIENT-SIDE. No server, no build step, no backend. Do not confuse with server-based playgrounds.

CRITICAL: All SDK methods are async (return Promises). Always await them or use .then().

Sub-Skills

TaskSub-Skill
Quick start for beginnerslivecodes/getting-started/SKILL.md
Create embedded playgroundslivecodes/sdk-embedding/SKILL.md
Use SDK methods (run, getCode, setConfig, watch)livecodes/sdk-methods/SKILL.md
Compress/decompress config utilitieslivecodes/sdk-embedding/SKILL.md
Configure via Config object, query paramslivecodes/configuration/SKILL.md
Choose display mode (full, simple, result, etc.)livecodes/display-modes/SKILL.md
Run playgrounds without visible UIlivecodes/headless-mode/SKILL.md
Import/export code (GitHub, gists, files)livecodes/import-export/SKILL.md
Work with 90+ languages and processorslivecodes/language-support/SKILL.md
Import npm packages without bundlerlivecodes/module-resolution/SKILL.md
Write and run tests in the playgroundlivecodes/testing/SKILL.md
Use with React, Vue, Svelte, Solid, Preactlivecodes/framework-wrappers/SKILL.md
Integrate with docs sites (Docusaurus, Astro)livecodes/markdown-integration/SKILL.md
Self-host on your own serverlivecodes/self-hosting/SKILL.md
Preview PRs in LiveCodes (GitHub Action)livecodes/gh-action/SKILL.md

Quick Decision Tree

New to LiveCodes?
  → livecodes/getting-started

Need to embed a playground in your app?
  → livecodes/sdk-embedding

Need to control playground programmatically?
  → livecodes/sdk-methods

Need to configure project content (languages, theme, etc.)?
  → livecodes/configuration

Need to show code readonly or result-only?
  → livecodes/display-modes

Need to run playground without any UI?
  → livecodes/headless-mode

Need to use React/Vue/Svelte/etc.?
  → livecodes/framework-wrappers

Need to import npm packages or external modules?
  → livecodes/module-resolution

Need a specific language (Python, SASS, TypeScript)?
  → livecodes/language-support

Need to run tests in the playground?
  → livecodes/testing

Need to import code from GitHub/URL or export?
  → livecodes/import-export

Need to add playgrounds to markdown docs?
  → livecodes/markdown-integration

Need to host LiveCodes on your own server?
  → livecodes/self-hosting

Need to preview PR changes in playgrounds?
  → livecodes/gh-action

Minimal Working Example

CDN (quickest)

html
<!doctype html>
<html>
  <head>
    <title>LiveCodes Demo</title>
  </head>
  <body>
    <div id="container"></div>
    <script type="module">
      import { createPlayground } from 'https://cdn.jsdelivr.net/npm/livecodes';

      createPlayground('#container', {
        config: {
          markup: { language: 'html', content: '<h1>Hello LiveCodes!</h1>' },
          style: { language: 'css', content: 'h1 { color: blue; }' },
          script: { language: 'javascript', content: 'console.log("Hello!");' },
        },
      });
    </script>
  </body>
</html>

NPM

bash
npm install livecodes
javascript
import { createPlayground } from 'livecodes';

const playground = await createPlayground('#container', {
  config: {
    markup: { language: 'html', content: '<h1>Hello!</h1>' },
  },
});

// SDK methods are async - always await
await playground.run();
const code = await playground.getCode();

React

jsx
import { useState } from 'react';
import LiveCodes from 'livecodes/react';

export default function App() {
  const [playground, setPlayground] = useState(null);

  return (
    <>
      <LiveCodes
        config={{ markup: { language: 'html', content: '<h1>Hello!</h1>' } }}
        sdkReady={setPlayground}
      />
      <button onClick={() => playground?.run()}>Run</button>
    </>
  );
}

Common Mistakes

HIGH: SDK methods return Promises - always await

javascript
// WRONG - code is a Promise, not actual code
const code = playground.getCode();
console.log(code.markup); // undefined!

// CORRECT - await the Promise
const code = await playground.getCode();
console.log(code.markup.content); // '<h1>Hello!</h1>'

HIGH: Container must exist before createPlayground

javascript
// WRONG - container doesn't exist yet
createPlayground('#container', { config }); // throws if #container not in DOM

// CORRECT - ensure container exists
const container = document.querySelector('#container');
if (container) {
  createPlayground('#container', { config });
}

// OR use headless mode if no UI needed
createPlayground({ headless: true, config });

HIGH: Config vs EmbedOptions confusion

javascript
// WRONG - appUrl is not a config property
createPlayground('#container', {
  config: {
    appUrl: 'https://my-server.com', // ERROR: wrong place
  },
});

// CORRECT - appUrl is an EmbedOption, not config
createPlayground('#container', {
  appUrl: 'https://my-server.com', // EmbedOptions
  config: {
    // Config
    markup: { language: 'html', content: '<h1>Hi</h1>' },
  },
});

MEDIUM: Different CDN imports create separate module instances

javascript
// WRONG - two different React instances
import React from 'react'; // esm.sh
import { createRoot } from 'skypack:react-dom/client'; // Different React!

// CORRECT - use same CDN consistently
import React from 'react';
import { createRoot } from 'react-dom/client'; // Both from esm.sh (default)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Livecodes AI skill do?

Open-source, client-side code playground supporting 90+ languages/frameworks. Runs entirely in the browser with SDK for embedding. Entry point for all LiveCodes skills.

Why use Livecodes on TypingMind?

Because you install it once and use it with any model. Livecodes is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Livecodes in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/live-codes/livecodes/tree/develop/.agents/skills/livecodes. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Livecodes?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Livecodes?

As many as you like. As long as a model supports skills, you can use Livecodes with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Livecodes AI skill free?

Yes. It is published on GitHub by live-codes under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇