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

# Deploy AnythingLLM

> Set up AnythingLLM and connect its dependencies with Spring Winter.

## Deploy with an agent

Copy agent prompt

Help me deploy AnythingLLM. Read [https://docs.springwinter.dev/deploy/open-source/anythingllm](https://docs.springwinter.dev/deploy/open-source/anythingllm.md), [https://docs.anythingllm.com/installation-docker/quickstart](https://docs.anythingllm.com/installation-docker/quickstart), and [https://docs.springwinter.dev/api-reference/agents](https://docs.springwinter.dev/api-reference/agents.md). Fetch the public OpenAPI specification from my Spring Winter origin. Use my local SPRINGWINTER\_TOKEN or existing SPRINGWINTER\_API\_TOKEN. Keep credentials out of chat, logs and source.

Confirm my project, AWS connection, Region and budget. Pin a release. Check its required services, container port, health path, network access and durable storage. Data requirements for this deployment: No separate SQL service for the standard Docker setup. It needs durable workspace storage. An external vector database is optional.

1. Choose a persistent container host for the standard image. Attach durable storage at /app/server/storage and set STORAGE\_DIR to that path as directed by the upstream Docker setup.
2. If you choose an external vector database, create it first and obtain its endpoint and scoped credentials. Prepare the model and embedding provider credentials too.
3. Start the pinned mintplexlabs/anythingllm image on port 3001 behind HTTPS with access controls. Complete initial setup, then connect the model, embedding and vector providers in the application.
4. Verify the providers before importing documents. Connect any Spring Winter application that calls AnythingLLM only after the endpoint is ready.

Show me the planned resources, database and migration order, secret names and estimated cost. Identify components that require separate hosting. Wait for approval before making changes. Include any planned restart, task replacement or restore in that approval. Use documented Spring Winter operations and wait for each workflow to finish. Import a non-sensitive document, ask a question about it, and confirm the workspace and document still work after restart. Report resource links and anything you could not verify.

## Before you start

[Connect your AWS account](https://docs.springwinter.dev/connect-aws.md) and choose a project. Review the [upstream deployment instructions](https://docs.anythingllm.com/installation-docker/quickstart) for the release you plan to pin.

## Data dependencies

No separate SQL service for the standard Docker setup. It needs durable workspace storage. An external vector database is optional.

## Deployment order

1. Choose a persistent container host for the standard image. Attach durable storage at `/app/server/storage` and set `STORAGE_DIR` to that path as directed by the upstream Docker setup.
2. If you choose an external vector database, create it first and obtain its endpoint and scoped credentials. Prepare the model and embedding provider credentials too.
3. Start the pinned `mintplexlabs/anythingllm` image on port 3001 behind HTTPS with access controls. Complete initial setup, then connect the model, embedding and vector providers in the application.
4. Verify the providers before importing documents. Connect any Spring Winter application that calls AnythingLLM only after the endpoint is ready.

Use [Runtime variables](https://docs.springwinter.dev/concepts/environment-variables.md) for runtime credentials. For a [Spring Winter web server](https://docs.springwinter.dev/deploy/web-servers.md), set an app-supported health path that returns HTTP 200 without credentials. Check **History** before running the application check.

## Verify the deployment

Import a non-sensitive document, ask a question about it, and confirm the workspace and document still work after restart.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.