> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Develop agents

> Develop agents on the LangSmith Agent Server runtime—capabilities, configuration, composition, and operations.

Develop your agents on the [Agent Server](/langsmith/agent-server) runtime. Once deployed, agents work with three primitives: [**assistants**](/langsmith/assistants) for configuration, [**threads**](/langsmith/use-threads) for state, and [**runs**](/langsmith/runs) for workloads. The pages in this tab cover the capabilities Agent Server provides, how to develop and [structure your application](/langsmith/application-structure), and how to [secure](/langsmith/auth) and [customize](/langsmith/custom-routes) the server.

## Capabilities

<CardGroup cols={2}>
  <Card title="Develop your application" cta="Set up your project" href="/langsmith/application-structure" icon="code">
    Structure your app, configure dependencies for Python, JavaScript, and monorepos, and connect agents with RemoteGraph, semantic search, TTLs, and CI/CD.
  </Card>

  <Card title="Agent Server runtime" cta="Explore the runtime" href="/langsmith/agent-server" icon="bolt">
    Work with assistants, threads, runs, and cron jobs. Stream to users, pause for human review, handle concurrent input, and connect via MCP and A2A.
  </Card>

  <Card title="Auth & access control" cta="Secure your server" href="/langsmith/auth" icon="lock">
    Authenticate users, enforce resource-level access, and connect external OAuth2 identity providers.
  </Card>

  <Card title="Server customization" cta="Customize your server" href="/langsmith/caching" icon="settings">
    Add caching, custom stores and checkpointers, lifespan hooks, middleware, custom routes, encryption, and configurable headers and logs.
  </Card>
</CardGroup>

## Tutorials

* [Collect user feedback for Agent Server runs](/langsmith/agent-server-feedback): Attach end-user feedback to runs and traces
* [Deploy other frameworks (e.g., Strands, CrewAI)](/langsmith/deploy-other-frameworks): Wrap existing agents with Functional API and deploy
* [Implement generative user interfaces with LangGraph](/langsmith/generative-ui-react): Stream UI elements to a React client
* [Implement a CI/CD pipeline](/langsmith/cicd-pipeline-example): Automate tests, evaluations, and deployments with GitHub Actions

## Securing and customizing your server

* [Custom auth](/langsmith/auth): Authentication and multi-tenant access control
* [Server customization](/langsmith/custom-routes): Custom routes, [middleware](/langsmith/custom-middleware), [lifespan hooks](/langsmith/custom-lifespan), [encryption](/langsmith/encryption)

## Operations

* [CI/CD pipelines](/langsmith/cicd-pipeline-example)
* [TTL configuration](/langsmith/configure-ttl) for state and thread management
* [Semantic search](/langsmith/semantic-search)

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/develop-agents-overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>