Skip to content

chore: fix home page styling #892

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 14, 2025
Merged

chore: fix home page styling #892

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
235 changes: 115 additions & 120 deletions src/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,124 +4,119 @@ sidebarTitle: All docs
mode: "custom"
---

# Documentation

LangChain is the platform for agent engineering. AI teams at Replit, Clay, Rippling, Cloudflare, Workday, and more trust LangChain's products to engineer reliable agents.

Our **open source frameworks** help you build agents:

- [**LangChain**](/oss/python/langchain/overview) helps you quickly get started building agents, with any model provider of your choice.
- [**LangGraph**](/oss/python/langgraph/overview) allows you to control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support. You can manage long-running tasks with durable execution.

[**LangSmith**](/langsmith/home) is a platform that helps AI teams use live production data for continuous testing and improvement. LangSmith provides:

- **Observability** to see exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics.
- **Evaluation** to test and score agent behavior on production data and offline datasets for continuous improvement.
- **Deployment** to ship your agent in one click, using scalable infrastructure built for long-running tasks.

## Get started

<CardGroup cols={4}>

<Card title="Build your first agent" icon="gear" href="/oss/python/langchain/quickstart" cta="Get started" />

<Card title="Sign up for LangSmith" icon="screwdriver-wrench" href="https://smith.langchain.com/" cta="Try LangSmith" />

<Card title="Send your first trace" icon="monitor-waveform" href="/langsmith/integrations" cta="Get started" />

<Card title="Build an advanced agent" icon="gears" href="/oss/python/langgraph/quickstart" cta="Get started"/>

</CardGroup>

## Open source agent frameworks

<Tabs>
<Tab title="Python" icon="python">

<CardGroup cols={2}>
<Card
title="LangChain"
href="/oss/python/langchain/overview"
icon="link"
cta="Learn more"
>
Quickly get started building agents, with any model provider of your choice.
</Card>

<Card
title="LangGraph"
href="/oss/python/langgraph/overview"
icon="circle-nodes"
cta="Learn more"
>
Control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support.
</Card>

</CardGroup>

</Tab>
<Tab title="JavaScript" icon="js">
<CardGroup cols={2}>
<Card
title="LangChain"
href="/oss/javascript/langchain/overview"
icon="link"
cta="Learn more"
>
Quickly get started building agents, with any model provider of your choice.
</Card>

<Card
title="LangGraph"
href="/oss/javascript/langgraph/overview"
icon="circle-nodes"
cta="Learn more"
>
Control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support.
</Card>

</CardGroup>
</Tab>
</Tabs>

## LangSmith

<CardGroup cols={1}>
<Card
title="Observability"
href="/langsmith/observability"
icon="magnifying-glass"
cta="Learn more"
>
See exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics.
</Card>

<Card
title="Evaluation"
href="/langsmith/evaluation"
icon="chart-simple"
cta="Learn more"
>
Test and score agent behavior on production data or offline datasets to continuously improve performance.
</Card>

<Card
title="Prompt Engineering"
href="/langsmith/prompt-engineering"
icon="terminal"
cta="Learn more"
>
Iterate on prompts with version control, prompt optimization, and collaboration features.
</Card>

<Card
title="Deployment"
href="/langsmith/deployments"
icon="rocket-launch"
cta="Learn more"
>
Ship your agent in one click, using scalable infrastructure built for long-running tasks.
</Card>

</CardGroup>

<div class="mx-auto max-w-8xl px-0 lg:px-5" style={{ paddingBottom: "8rem" }}>
<div class="mdx-content prose prose-gray dark:prose-invert mx-4 pt-10">
<h1 class="flex whitespace-pre-wrap group font-semibold text-2xl sm:text-3xl mt-8">Documentation</h1>

LangChain is the platform for agent engineering. AI teams at Replit, Clay, Rippling, Cloudflare, Workday, and more trust LangChain's products to engineer reliable agents.

Our **open source frameworks** help you build agents:

- [**LangChain**](/oss/python/langchain/overview) helps you quickly get started building agents, with any model provider of your choice.
- [**LangGraph**](/oss/python/langgraph/overview) allows you to control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support. You can manage long-running tasks with durable execution.

[**LangSmith**](/langsmith/home) is a platform that helps AI teams use live production data for continuous testing and improvement. LangSmith provides:

- **Observability** to see exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics.
- **Evaluation** to test and score agent behavior on production data and offline datasets for continuous improvement.
- **Deployment** to ship your agent in one click, using scalable infrastructure built for long-running tasks.

<h2 class="flex whitespace-pre-wrap group font-semibold">Get started</h2>

<CardGroup cols={4}>
<Card title="Build your first agent" icon="gear" href="/oss/python/langchain/quickstart" cta="Get started" />
<Card title="Sign up for LangSmith" icon="screwdriver-wrench" href="https://smith.langchain.com/" cta="Try LangSmith" />
<Card title="Send your first trace" icon="monitor-waveform" href="/langsmith/integrations" cta="Get started" />
<Card title="Build an advanced agent" icon="gears" href="/oss/python/langgraph/quickstart" cta="Get started"/>
</CardGroup>

<h2 class="flex whitespace-pre-wrap group font-semibold">Open source agent frameworks</h2>

<Tabs>
<Tab title="Python" icon="python">
<CardGroup cols={2}>
<Card
title="LangChain"
href="/oss/python/langchain/overview"
icon="link"
cta="Learn more"
>
Quickly get started building agents, with any model provider of your choice.
</Card>
<Card
title="LangGraph"
href="/oss/python/langgraph/overview"
icon="circle-nodes"
cta="Learn more"
>
Control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support.
</Card>
</CardGroup>
</Tab>
<Tab title="JavaScript" icon="js">
<CardGroup cols={2}>
<Card
title="LangChain"
href="/oss/javascript/langchain/overview"
icon="link"
cta="Learn more"
>
Quickly get started building agents, with any model provider of your choice.
</Card>
<Card
title="LangGraph"
href="/oss/javascript/langgraph/overview"
icon="circle-nodes"
cta="Learn more"
>
Control every step of your custom agent with low-level orchestration, memory, and human-in-the-loop support.
</Card>
</CardGroup>
</Tab>
</Tabs>

<h2 class="flex whitespace-pre-wrap group font-semibold">LangSmith</h2>

<CardGroup cols={1}>
<Card
title="Observability"
href="/langsmith/observability"
icon="magnifying-glass"
cta="Learn more"
>
See exactly how your agent thinks and acts with detailed tracing and aggregate trend metrics.
</Card>
<Card
title="Evaluation"
href="/langsmith/evaluation"
icon="chart-simple"
cta="Learn more"
>
Test and score agent behavior on production data or offline datasets to continuously improve performance.
</Card>
<Card
title="Prompt Engineering"
href="/langsmith/prompt-engineering"
icon="terminal"
cta="Learn more"
>
Iterate on prompts with version control, prompt optimization, and collaboration features.
</Card>
<Card
title="Deployment"
href="/langsmith/deployments"
icon="rocket-launch"
cta="Learn more"
>
Ship your agent in one click, using scalable infrastructure built for long-running tasks.
</Card>
</CardGroup>
</div>
</div>

{/* hack way to hide the callout cards*/}
<div className="relative">
<div className="absolute top-0 left-0 w-screen h-20 dark:bg-background-dark z-10">
</div>
</div>