Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

4.9 KB
Raw Blame
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta http-equiv="refresh" content="0;url=/latest/">
<link rel="canonical" href="https://__SITE_DOMAIN__/latest/">
<title>Pipelex — Turn your expertise into an AI-powered App, MCP or API</title>
<meta name="description" content="Pipelex lets you build AI methods with your coding agent and run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.">
<meta property="og:title" content="Pipelex — Turn your expertise into an AI-powered App, MCP or API">
<meta property="og:description" content="Pipelex lets you build AI methods with your coding agent and run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.">
<meta property="og:url" content="https://__SITE_DOMAIN__/latest/">
<meta property="og:type" content="website">
<style>
    body {
        margin: 0;
        padding: 2rem;
        background: #1a1a1a;
        color: #d4d4d4;
        font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
        line-height: 1.6;
        max-width: 720px;
        margin: 0 auto;
    }
    a { color: #45BF9F; }
    h1 { color: #e5e5e5; }
    ul { padding-left: 1.2rem; }
    .redirect-notice { color: #888; font-size: 0.85rem; margin-top: 2rem; }
</style>
</head>
<body>
<h1>Pipelex: Turn your expertise into an AI-powered App, MCP or API</h1>
<p>Describe how the work gets done in plain English, and your coding agent builds it into a method with the Pipelex plugin. A method is a multi-step, deterministic AI procedure that chains LLMs, OCR, image generation and more. Then run it as a webapp for your team or as SaaS for your customers, as an MCP for chatbots, or via API for your software.</p>
<h2>Get Started</h2>
<ul>
<li><a href="/latest/get-started/quick-start/">Quick Start</a> — Sign up at <a href="https://app.pipelex.com">app.pipelex.com</a>, install the Pipelex plugin in Claude Code or Codex, and ask your agent for the method you want.</li>
<li><a href="/latest/get-started/run-it-yourself/">Run It Yourself</a> — Install the Pipelex runtime and run methods on your own machine.</li>
<li><a href="/latest/get-started/mthds-language-tutorial/">MTHDS Language Tutorial</a> — Learn concepts, pipes, sequences, and structured outputs.</li>
<li><a href="/latest/cookbook/">Cookbook</a> — Example methods you run by their address, each with a page showing every way to use it.</li>
</ul>
<h2>What a Method Looks Like</h2>
<p>A method is a reusable, typed AI procedure, written in <a href="https://mthds.ai/latest/">MTHDS</a>, an open standard, and saved as a .mthds file. Each step is explicit, each output is structured, and every run is repeatable.</p>
<pre><code>[pipe.summarize_article]
type    = "PipeLLM"
inputs  = { article = "Text", audience = "Text" }
output  = "Text"
prompt  = "Summarize $article in three bullet points for $audience."
</code></pre>
<p>From here, Pipelex handles model routing across 60+ models, structured output parsing, and pipeline orchestration.</p>
<h2>Why Methods?</h2>
<ul>
<li><strong>Declarative</strong> — Express business logic in human-readable .mthds files that work across models.</li>
<li><strong>Typed</strong> — Concepts are semantic types: AI understands what you mean, and every input and output connects with purpose.</li>
<li><strong>Repeatable</strong> — Deterministic orchestration that leaves exactly the room you want for AI to express its intelligence.</li>
<li><strong>Composable</strong> — Chain pipes into sequences, nest methods inside methods, and share them with the community.</li>
</ul>
<h2>Capabilities</h2>
<ul>
<li><a href="/latest/features/concepts/">Typed Concepts</a> — Semantic types that give meaning to every input and output.</li>
<li><a href="/latest/features/pipe-operators/">Pipe Operators</a> — LLM calls, document extraction, image generation, web search, composition, and custom functions.</li>
<li><a href="/latest/features/pipeline-orchestration/">Pipeline Orchestration</a> — Sequence, parallel, batch, and conditional controllers.</li>
<li><a href="/latest/features/llm-integration/">60+ AI Models</a> — OpenAI, Anthropic, Mistral, Google, Deepseek, Hugging Face, and more.</li>
<li><a href="/latest/features/validation-dry-run/">Validation and Dry Run</a> — Catch errors without spending tokens.</li>
<li><a href="/latest/features/cli/">CLI and Tooling</a> — Init, build, validate, run, and graph visualization.</li>
</ul>
<h2>The MTHDS Ecosystem</h2>
<ul>
<li><a href="https://mthds.ai">mthds.ai</a> — The MTHDS language specification</li>
<li><a href="https://mthds.sh">mthds.sh</a> — The Methods Hub for discovering and sharing methods</li>
<li><a href="https://github.com/Pipelex/pipelex">GitHub</a> — Pipelex source code</li>
</ul>
<p>For AI agents: see <a href="/llms.txt">/llms.txt</a> for a machine-readable index of this documentation.</p>
<p class="redirect-notice">Redirecting to <a href="/latest/">Pipelex Documentation</a>&#8230;</p>
</body>
</html>