Contributing ↗

    This issue is blocked by #123 and related to #456.
    ```
  </Accordion>

  <Accordion title="Suggest features" icon="wand">
Have an idea for a new feature or enhancement?

<span class="steps-start"></span>
  <span class="step-marker" data-step-title="Search"></span>
    Search the issues for the respective repository for existing feature requests:

    <Columns cols={3}>
      <span class="card-start" data-card-title="LangChain" data-card-icon="link" data-card-href="https://github.com/langchain-ai/langchain/issues?q=state%3Aopen%20label%3A%22feature%20request%22"></span>Issues<span class="card-end"></span>
      <span class="card-start" data-card-title="LangGraph" data-card-icon="topology-ring" data-card-href="https://github.com/langchain-ai/langgraph/issues?q=state%3Aopen%20label%3Aenhancement"></span>Issues<span class="card-end"></span>
      <span class="card-start" data-card-title="Deep Agents" data-card-icon="robot" data-card-href="https://github.com/langchain-ai/deepagents/issues?q=is%3Aissue%20state%3Aopen%20label%3Afeature"></span>Issues<span class="card-end"></span>
    
  <span class="step-end"></span>

  <span class="step-marker" data-step-title="Discuss"></span>
    If no requests exist, start a new discussion under the [relevant category](https://forum.langchain.com/c/help/langchain/14) so that project maintainers and the community can provide feedback.
  <span class="step-end"></span>

  <span class="step-marker" data-step-title="Describe"></span>
    Be sure to describe the use case and why it would be valuable to others. If possible, provide examples or mockups where applicable. Outline test cases that should pass.
  <span class="step-end"></span>
<span class="steps-end"></span>
  </Accordion>

  <Accordion title="Improve documentation" icon="book">
Documentation improvements are always welcome! We strive to keep our docs clear and comprehensive, and your perspective can make a big difference.

<span class="card-start" data-card-title="How to propose changes to the documentation" data-card-href="/oss/python/contributing/documentation"></span>Guide<span class="card-end"></span>
  </Accordion>

  <Accordion title="Contribute code" icon="code">
With a large userbase, it can be hard for our small team to keep up with all the feature requests and bug fixes. If you have the skills and time, we would love your help!

<span class="card-start" data-card-title="How to make your first Pull Request" data-card-href="/oss/python/contributing/code"></span>Guide<span class="card-end"></span>

If you start working on an issue, please assign it to yourself or ask a maintainer to do so. This helps avoid duplicate work.

If you are looking for something to work on, check out the issues labeled "good first issue" or "help wanted" in our repos:

<Columns cols={3}>
  <span class="card-start" data-card-title="LangChain" data-card-icon="link" data-card-href="https://github.com/langchain-ai/langchain/labels"></span>Labels<span class="card-end"></span>
  <span class="card-start" data-card-title="LangGraph" data-card-icon="topology-ring" data-card-href="https://github.com/langchain-ai/langgraph/labels"></span>Labels<span class="card-end"></span>
  <span class="card-start" data-card-title="Deep Agents" data-card-icon="robot" data-card-href="https://github.com/langchain-ai/deepagents/labels"></span>Labels<span class="card-end"></span>

  </Accordion>

  <Accordion title="Add a new integration" icon="plug-connected">
<span class="card-start" data-card-title="LangChain" data-card-icon="link" data-card-href="/oss/python/contributing/integrations-langchain"></span>Guide to adding a new LangChain integration<span class="card-end"></span>
<span class="card-start" data-card-title="Deep Agents sandboxes" data-card-icon="cube" data-card-href="/oss/python/contributing/integrations-langchain"></span>Guide to contributing a sandbox integration<span class="card-end"></span>
  </Accordion>
</AccordionGroup>

## Acceptable uses of LLMs

Generative AI can be a useful tool for contributors, but like any tool should be used with critical thinking and good judgement.

We encourage contributors to use AI tools efficiently where they help. However, AI assistance must be paired with meaningful human intervention, judgement, and contextual understanding. **If the human effort required to create a pull request is less than the effort required for maintainers to review it, that contribution should not be submitted.**

We struggle when contributors' entire work (code changes, documentation updates, pull request descriptions) are LLM-generated. These drive-by contributions often mean well but miss the mark in terms of contextual relevance, accuracy, and quality. Mass automated contributions like these represent a denial-of-service attack on our human effort.

**We will close pull requests and issues that appear to be low-effort, AI-generated spam.**

With great tools comes great responsibility.

***

<span class="callout-start" data-callout-type="note"></span>
  [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/contributing/overview.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
<span class="callout-end"></span>

<span class="callout-start" data-callout-type="note"></span>
  [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
<span class="callout-end"></span>