The LangChain open source stack provides the building blocks you need to design, test, and ship agents. Each layer is yours to configure: the model, the tools, the context and memory an agent works from, and the harness around the model loop.
<h2 class="flex whitespace-pre-wrap group font-semibold">Choose your starting point</h2>
Deep Agents, LangChain, and LangGraph share the same open source stack, so choose based on how much control you need. For managed hosting or no-code, start with Managed Deep Agents or Fleet:
<Tabs>
<Tab title="Python">
<CardGroup cols={3}>
<Card
title="Deep Agents"
cta="Get started"
href="/oss/python/deepagents/overview"
icon="/images/brand/deep-agents-icon.png"
>
Build agents for complex, long-running tasks. A complete agent harness with planning, subagents, a virtual filesystem, and long-term memory built in. The fastest way to start.
</Card>
<Card
title="Managed Deep Agents"
cta="Get started"
href="/langsmith/python/managed-deep-agents-overview"
icon="/images/brand/deep-agents-icon.png"
>
Build deep agents with managed deployment infrastructure. You write the agent; LangSmith runs the harness and runtime.
</Card>
<Card
title="LangChain"
cta="Get started"
href="/oss/python/langchain/overview"
icon="/images/brand/langchain-icon.png"
>
A minimal, configurable agent framework. Compose exactly what you need from models, tools, prompts, and middleware.
</Card>
<Card
title="LangGraph"
cta="Get started"
href="/oss/python/langgraph/overview"
icon="/images/brand/langgraph-icon.png"
>
Low-level orchestration for stateful, long-running agents: durable execution, streaming, memory, and human-in-the-loop.
</Card>
<Card
title="Prefer no-code?"
cta="View Fleet"
href="/langsmith/fleet"
icon="wand"
type="tip"
className="card-tip"
>
Build and run agents without writing code using LangSmith Fleet.
</Card>
</CardGroup>
</Tab>
<Tab title="TypeScript">
<CardGroup cols={3}>
<Card
title="Deep Agents"
cta="Get started"
href="/oss/javascript/deepagents/overview"
icon="/images/brand/deep-agents-icon.png"
>
Build agents for complex, long-running tasks. A complete agent harness with planning, subagents, a virtual filesystem, and long-term memory built in. The fastest way to start.
</Card>
<Card
title="Managed Deep Agents"
cta="Get started"
href="/langsmith/javascript/managed-deep-agents-overview"
icon="/images/brand/deep-agents-icon.png"
>
Build deep agents with managed deployment infrastructure. You write the agent; LangSmith runs the harness and runtime.
</Card>
<Card
title="LangChain"
cta="Get started"
href="/oss/javascript/langchain/overview"
icon="/images/brand/langchain-icon.png"
>
A minimal, configurable agent framework. Compose exactly what you need from models, tools, prompts, and middleware.
</Card>
<Card
title="LangGraph"
cta="Get started"
href="/oss/javascript/langgraph/overview"
icon="/images/brand/langgraph-icon.png"
>
Low-level orchestration for stateful, long-running agents: durable execution, streaming, memory, and human-in-the-loop.
</Card>
<Card
title="Prefer no-code?"
cta="View Fleet"
href="/langsmith/fleet"
icon="wand"
type="tip"
className="card-tip"
>
Build and run agents without writing code using LangSmith Fleet.
</Card>
</CardGroup>
</Tab>
</Tabs>
<h2 class="flex whitespace-pre-wrap group font-semibold">Use a ready-made agent</h2>
<CardGroup cols={1}>
<Card
title="Deep Agents Code"
cta="Install and run"
href="/oss/deepagents/code/overview"
icon="code"
>
Open source terminal coding agent (`dcode`) built on the Deep Agents SDK. Switch models mid-session, customize skills and memory, and approve shell execution from the CLI.
</Card>
</CardGroup>
<h2 class="flex whitespace-pre-wrap group font-semibold">Explore</h2>
<Tabs>
<Tab title="Python">
<CardGroup cols={4}>
<Card
title="Integrations"
cta="Browse providers"
href="/oss/python/integrations/providers/overview"
icon="plug"
>
Connect to model providers, vector stores, retrievers, and other components.
</Card>
<Card
title="Learn"
cta="View tutorials"
href="/oss/python/learn"
icon="book"
>
Follow tutorials and conceptual guides for common agent patterns and use cases.
</Card>
<Card
title="Reference"
cta="View reference"
href="/oss/python/reference/overview"
icon="code"
>
API references, error codes, release notes, and migration guides.
</Card>
<Card
title="Contribute"
cta="Start contributing"
href="/oss/python/contributing/overview"
icon="heart-plus"
>
Contribute documentation, code, and integrations to the LangChain ecosystem.
</Card>
</CardGroup>
</Tab>
<Tab title="TypeScript">
<CardGroup cols={4}>
<Card
title="Integrations"
cta="Browse providers"
href="/oss/javascript/integrations/providers/overview"
icon="plug"
>
Connect to model providers, vector stores, retrievers, and other components.
</Card>
<Card
title="Learn"
cta="View tutorials"
href="/oss/javascript/learn"
icon="book"
>
Follow tutorials and conceptual guides for common agent patterns and use cases.
</Card>
<Card
title="Reference"
cta="View reference"
href="/oss/javascript/reference/overview"
icon="code"
>
API references, error codes, release notes, and migration guides.
</Card>
<Card
title="Contribute"
cta="Start contributing"
href="/oss/javascript/contributing/overview"
icon="heart-plus"
>
Contribute documentation, code, and integrations to the LangChain ecosystem.
</Card>
</CardGroup>
</Tab>
</Tabs>
</div>