Back to Examples
Langbase
Discover Langbase's comprehensive language solutions with expert guides and resources designed to enhance your multilingual communication.
Lines
47,822
Sections
824
Want your own llms.txt file?
Generate a professional, AI-friendly file for your website in minutes!
llms.txt Preview
<doc>
<metadata>
<title>Page</title>
<url>https://langbase.com/docs/</url>
</metadata>
<content>
import { Guides } from '@/components/Guides';
import { Resources } from '@/components/Resources';
import { HeroPattern } from '@/components/HeroPattern';
import { generateMetadata } from '@/lib/generate-metadata';
<a href="https://langbase.com/studio" className="hidden lg:flex h-full w-full items-center justify-center mb-4">
<img src="/docs/logo-bg-black.svg" className="flex h-full w-full mt-0 shadow-[0_2px_3px_0_theme(colors.black/15%),0_0_0_1px_theme(colors.white/1%),0_-1px_0_0_theme(colors.white/2%)] rounded-[3rem]" />
</a>
<h1 className="flex lg:hidden">Langbase Docs</h1>
### Langbase is the most powerful serverless AI cloud for building and deploying AI agents.
Build, deploy, and scale serverless AI agents with tools and memory (RAG). Simple AI primitives no bloated frameworks, all with a world-class developer experience without using any frameworks.
<CTAButtons
primary={{ href: 'https://command.new', text: 'Vibe code AI agents', sub:'with Command.new' }}
secondary={{ href: '/examples/agent-architectures', text: 'Agent architectures', sub:'(no frameworks)' }}
/>
---
<ProductsTable />
---
## Why Langbase?
Langbase is the best way to build and deploy AI agents.
Our mission: AI for all. Not just ML wizards. Every. Single. Developer.
**Build AI agents without any bloated frameworks**. You write the logic, we handle the logistics.
Compared to complex AI frameworks, Langbase is serverless and [the first composable AI platform][composable].
1. Start by building simple [AI agents (pipes)](/pipe)
2. Then train serverless semantic [Memory agents (RAG)](/memory) to get accurate and trusted results
<Img
caption="Langbase — The most powerful serverless AI Agents platform"
light="https://raw.githubusercontent.com/LangbaseInc/docs-images/refs/heads/main/langbase/why-langbase.jpg"
dark="https://raw.githubusercontent.com/LangbaseInc/docs-images/refs/heads/main/langbase/why-langbase.jpg"
/>
---
<Resources />
---
<Guides />
---
<Note sub="Join today">
**Langbase is free for anyone to [get started][signup]**.
We process billions of AI messages tokens daily, used by thousands of developers. [Tweet][x] us — what will you ship with Langbase?
It all [started][start] with a developer thinking … GPT is amazing, I want it everywhere, that's what ⌘ Langbase does for me.
</Note>
{/* <Features /> */}
[pipe]: /pipe
[memory]: /memory
[studio]: https://studio.langbase.com
[composable]: /composable-ai
[start]: https://langbase.fyi/starting-langbase
[signup]: https://langbase.fyi/awesome
[x]: https://twitter.com/LangbaseInc
[li]: https://www.linkedin.com/company/langbase/
[email]: mailto:[email protected]?subject=Pipe-Quickstart&body=Ref:%20https://langbase.com/docs/pipe/quickstart
[api]: /api-reference
[sdk]: /sdk
</content>
</doc>
<doc>
<metadata>
<title>Workflow</title>
<url>https://langbase.com/docs/workflow/</url>
</metadata>
<content>
import { generateMetadata } from '@/lib/generate-metadata';
<LanguageProvider defaultLanguage='typescript'>
# Workflow
Workflow, an AI Primitive by Langbase, helps you build multi-step agentic applications by breaking them into simple steps with built-in durable features like timeouts and retries.
Building AI applications often requires orchestrating multiple operations that depend on each other. Workflow enables you to:
- Orchestrate operations in both sequential and parallel execution patterns
- Create conditional execution paths based on previous step results
- Implement resilient processes with configurable retry strategies
- Set time boundaries to prevent operations from running indefinitely
- Track execution flow with detailed step-by-step logging
<CTAButtons
primary={{ href: '/sdk/workflow', text: 'Start with Langbase SDK' }}
/>
---
## Quickstart
This workflow example shows how to build a simple email processing workflow that summarizes the email, analyzes the sentiment, and determines if a response is needed.
## Step #1: Generate Langbase API key
Every request you send to Langbase needs an [API key](/api-reference/api-keys). This guide assumes you already have one. If not, please check the instructions below.
<Spoiler title="Get your Langbase API key: User or Org">
You can generate API keys from the [Langbase Studio](https://studio.langbase.com) by following these steps:
1. Switch to your user or org account.
2. From the sidebar, click on the `API keys`.
3. From here you can create a new API key or manage existing ones.
For more details, follow the [Langbase API keys](/api-reference/api-keys) documentation.
</Spoiler>
---
## Step #2: Setup your project [lang]
Create a new directory for your project and navigate to it.
<CodeGroup exampleTitle="Project setup" title="Project setup">
```bash {{ title: 'bash' }}
mkdir langbase-workflow
cd langbase-workflow
```
</CodeGroup>
Preview of Langbase's llms.txt file. View complete file (47,822 lines) →
Ready to create yours?
Generate a professional llms.txt file for your website in minutes with our AI-powered tool.
Generate Your llms.txt File