AnythingLLM starter
AnythingLLM turns your documents into something you can ask questions of. Upload PDFs, Word files, spreadsheets, text or web pages into workspaces, and chat with them through OpenAI, Anthropic, Mistral, Gemini, OpenRouter or any OpenAI-compatible API, with answers that cite their sources. Embeddings are made by a small model that runs inside the app, so your documents are not sent to a third party just to be indexed, and the vector database lives alongside them. Deploying it adds a persistent volume, so workspaces, chats, documents and settings survive restarts and redeploys, with daily snapshots you can restore from the app's Volume tab. It is locked from the first start: the password is printed once to the deploy log, and you can switch to multi-user mode with separate accounts. Agents, an embeddable chat widget and a developer API are included. You bring the model key, and your provider bills the tokens.
The source
This template is an ordinary public repository. Read it, fork it, or open a pull request against it. Deploying pulls its default branch and builds it the same way velixir builds your own code.
velixirnet/template-anythingllmOnce it is live
The template is just a starting point. Clone it, edit it, then ship over the top with the CLI:
velixir deploy
Or add the GitHub Actions workflow from the app's Deploys tab to your repo, and every push to your deploy branch ships a release. Both run the same pipeline this template just went through.