Skip to main content
Make your integration available to the community.
Do not submit integration PRs to the LangChain or Deep Agents repositories.New integrations should be published as standalone npm packages under your own GitHub organization or account (for example, @your-org/langchain-yourservice), not as PRs to the langchain-ai/langchainjs repository.The main repository only contains a small subset of first-party integrations maintained by the LangChain team.
Publish your package to npm, then follow Make your integration discoverable below.

​
Make your integration discoverable

After publishing, open a PR in the LangChain docs repository so your package appears under the integrations tab. Which PR you open depends on eligibility for a hosted guide.

​
Eligibility for hosted guides

LangChain hosts full integration guides in this docs repo only when either:
  • The package has at least 50,000 monthly downloads on PyPI (or npm for TypeScript), or
  • Maintainers mark the integration as featured
If you do not meet either criterion, do not open a PR that adds a new docs page. Instead, add a YAML listing so the package appears in the component download table with a link to your own docs.

​
List in the download table (default)

Open a PR that adds an entry to scripts/data/integration_external_docs.yaml. Each entry needs at least:
  • name: LangChain class or display name (for example, ChatAI21).
  • pypi or npm: Registry package name used for the downloads badge.
  • docs_url: Link for the name column. Prefer partner docs, then the GitHub repo, then the PyPI or npm page.
Optionally include component-specific fields (for example, chat capability flags such as stream and tool_calling) so the table columns stay accurate. Follow existing entries in the same language and component section. After merge, the refresh job regenerates the component table snippets so your row appears alongside hosted integrations.
This PR is for listing metadata only. Host your usage docs on your site or GitHub README. Your integration package itself should live in its own repository under your GitHub organization or account, published as a standalone package.
If your package meets the eligibility criteria, create a documentation page from one of the following templates and open a PR in the docs repo. Depending on the type of integration you have built, you will need to create different types of documentation pages. LangChain provides templates for different types of integrations to help you get started.

Chat models

To reference existing documentation, you can look at the list of integrations and find similar ones to yours.To view a given documentation page in raw markdown, use the dropdown button next to “Copy page” on the top right of the page and select “View as Markdown”.
Make a fork of the LangChain docs repository (not the main langchain repo) under a personal GitHub account, and clone it locally. Create a new branch for your integration. Copy the template and modify it using your favorite markdown text editor. Make sure to refer to and follow the documentation guide when writing your documentation. If your package was previously listed in integration_external_docs.yaml, remove that YAML entry in the same PR so the table does not show a duplicate row. Do not set featured: true in frontmatter unless a maintainer asks you to. Featured status is a maintainer decision.
This PR is for documentation only. Your integration package itself should live in its own repository under your GitHub organization or account, published as a standalone package.
We may reject PRs or ask for modification if:
Please be patient as we handle a large volume of PRs. We will review your PR as soon as possible and provide feedback or merge it. Do not repeatedly tag maintainers about your PR.
If your PR includes AI-generated content, you must follow our acceptable uses of LLMs policy.

​
Next steps

Congratulations! Your integration is published and listed for the LangChain community.

Co-marketing

Get in touch with the LangChain marketing team to explore co-marketing opportunities.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.