Self-Hosted AI Stack

Open-source Docker Compose stack for private, self-hosted AI

Advanced API
Screenshot of Self-Hosted AI Stack, Open-source Docker Compose stack for private, self-hosted AI

What is Self-Hosted AI Stack?

Self-Hosted AI Stack is a chat tool. An MIT-licensed Docker Compose project that deploys local models, chat, document retrieval, transcription and speech on your own Linux server, with optional HTTPS and NVIDIA GPU support.

Self-Hosted AI Stack is an open-source Docker Compose project that bundles the pieces of a private AI setup into one deployable package. Instead of a hosted service, it is a set of configurations for running local language models, browser chat, document processing, speech transcription and speech generation on a Linux server the user controls, whether that is a machine at home or a cloud instance. The website itself only provides project information and resources; the software lives in a GitHub repository. The bundle combines several well-known components. Ollama runs local models, and AnythingLLM supplies a browser-based chat interface. Docling parses documents and embeddings support semantic search and retrieval over them. ScribeCrate handles audio transcription, while Kokoro generates speech. LiteLLM routes model requests through a single gateway, and an MCP Gateway connects supported tools. Fresh deployments generate API keys and set password protection for AnythingLLM, so a new install is not left open by default. In practice, the project suits developers, homelab enthusiasts and small teams who want AI features without sending data to outside providers. Deployment runs through Docker Compose, with optional HTTPS and optional NVIDIA GPU acceleration; CPU configurations also exist. Users can start from a preconfigured lightweight stack or edit the Compose files to run only the services they need. Memory and performance needs depend on which services and models are chosen, so hardware planning matters. Licensing is split. The stack's configuration is MIT licensed, while each included service and model keeps its own license. Costs come from hardware, cloud hosting and any external providers a user adds. A paid book, The Self-Hosted AI Builder's Guide, covers deployment, security, backups and daily operation, and a free readiness guide helps people assess their computer and compare local, cloud, managed and hybrid approaches. Compared with hosted chat platforms, it trades convenience for control, and it sits closer to a DIY infrastructure kit than to a polished product.

How do you use Self-Hosted AI Stack?

  1. 1Check your local AI readiness
    Use the free readiness guide to assess your computer, try one small model and compare local, cloud, managed and hybrid options before committing.
    Self-Hosted AI Stack — Check your local AI readiness
  2. 2Open the GitHub repository
    Review the architecture, included services, lightweight configurations and security defaults in the project repository.
    Self-Hosted AI Stack — Open the GitHub repository
  3. 3Choose your service combination
    Pick a preconfigured lightweight stack or customize the Compose configuration to run only the services you need, with optional HTTPS and NVIDIA GPU support.
  4. 4Deploy with Docker Compose
    Run the stack on your own Linux server, locally or in the cloud. A fresh deployment generates API keys and sets password protection for AnythingLLM.
  5. 5Go deeper with the guide
    The Self-Hosted AI Builder's Guide covers deployment, security, backups and everyday operation for running the stack over time.
    Self-Hosted AI Stack — Go deeper with the guide

Pros and cons

Pros

  • Keeps models, documents and audio on infrastructure you control instead of a third-party serviceAI
  • Bundles chat, document parsing, transcription, speech and gateways into one Compose deploymentAI
  • Generates API keys and enables password protection for AnythingLLM on fresh installsAI
  • Lightweight preconfigured stacks and editable Compose files let you run only the services you needAI
  • Stack configuration is MIT licensed, and a free readiness guide helps size hardware before spendingAI

Cons

  • Requires your own Linux server and comfort with Docker Compose, so it is not a point-and-click productAI
  • Memory and performance needs vary by model, and hardware or cloud hosting costs fall on the userAI
  • Included services and models carry separate licenses that must be reviewed individuallyAI
  • The homepage gives no details on support channels, so help likely relies on GitHub and the paid bookAI

How much does Self-Hosted AI Stack cost?

Pricing

The stack's configuration is MIT licensed and free. Included services and models keep their own licenses, and hardware, cloud hosting and external providers may cost money. A companion book is sold on Amazon; a readiness guide is free.

Learn more

Integrations

Bundles Ollama, AnythingLLM, Docling, ScribeCrate, Kokoro, LiteLLM and MCP Gateway for supported tools. External model providers can be used through the gateway, though they may add costs.

Learn more

Features

Runs local models with Ollama, browser chat with AnythingLLM, document parsing with Docling plus embeddings for retrieval, transcription with ScribeCrate, speech with Kokoro, LiteLLM routing and MCP Gateway tool connections. Optional HTTPS and NVIDIA GPU acceleration.

Learn more

Frequently asked questions about Self-Hosted AI Stack

  • How much does Self-Hosted AI Stack cost?
    The stack's configuration is MIT licensed and free. Included services and models keep their own licenses, and hardware, cloud hosting and external providers may cost money. A companion book is sold on Amazon; a readiness guide is free.
  • Does Self-Hosted AI Stack have an API?
    Yes, Self-Hosted AI Stack offers an API.
  • How do you use Self-Hosted AI Stack?
    The walkthrough on this page covers 5 steps: 1. Check your local AI readiness 2. Open the GitHub repository 3. Choose your service combination 4. Deploy with Docker Compose 5. Go deeper with the guide.
  • What platforms does Self-Hosted AI Stack support?
    Self-Hosted AI Stack is available on Linux.
  • What does Self-Hosted AI Stack integrate with?
    Bundles Ollama, AnythingLLM, Docling, ScribeCrate, Kokoro, LiteLLM and MCP Gateway for supported tools. External model providers can be used through the gateway, though they may add costs.
  • What are the limitations of Self-Hosted AI Stack?
    Requires your own Linux server and comfort with Docker Compose, so it is not a point-and-click product. Memory and performance needs vary by model, and hardware or cloud hosting costs fall on the user. Included services and models carry separate licenses that must be reviewed individually.

Status

StatusActive
Views0
Outbound clicks0
Added10/7/2026

Platforms

Linux

Pricing

Free