Skip to main content
Enclave
Tutorials / Self-hosting

How to self-host an AI assistant? Enclave in three steps

The simplest path to self-hosting an AI assistant is Docker: clone the open-source repo, copy the environment variables, and start with a single docker compose. Enclave is exactly such an AI assistant world — MIT open source and running on your own machine in three steps.

Last reviewed:

The short answer

Self-host an AI assistant in three steps: clone the repo → copy .env → docker compose up. Enclave is MIT open source, with the full stack running locally.

Key points at a glance

  • If you've used docker compose, it's about as hard as running an ordinary web service.
  • Three steps: clone the repo → configure .env → docker compose up.
  • The API, frontend, database, and vector index all run locally — your data never leaves the machine.

Step 1: Prepare a machine that can run Docker

You need a machine with Docker and docker compose installed — an ordinary cloud server or home host will do. If you only use cloud model APIs, no GPU is required; you only need compute when you want to run local models. First confirm that Docker runs properly.

Step 2: Clone the repo and configure .env

Clone the Enclave repo from GitHub, copy the .env template to .env, and fill in the necessary settings as instructed (for example, the model API keys you want to connect). All configuration lives in this one file — just follow the repo README and deployment docs.

Step 3: Start with a single docker compose

Run docker compose up, and Enclave's API, frontend, database, and vector index all come up locally together. Once it's started, open the corresponding address in your browser to enter a private assistant world that's entirely yours, with data stored only on your own machine. Later, git pull + docker compose up -d is all you need to upgrade.

FAQ

  • Can I self-host Enclave? Is it hard?
    Yes, and it's about as hard as running an ordinary web service. If you've used docker compose, three steps get you your own instance: clone the repo, copy .env, and docker compose up. The API, frontend, database, and vector index all run on your own machine.
  • What do I need to self-host Enclave? Do I need a GPU?
    Not necessarily a GPU. If you use cloud model APIs (OpenAI, Anthropic, etc.), an ordinary server or home machine that can run Docker is enough — inference happens in the cloud, and your machine only runs the app and database. You only need the corresponding VRAM and compute if you want offline inference with local models (Ollama / vLLM).
  • How do I update a self-hosted Enclave to a new version?
    Run git pull to fetch the latest code, then docker compose up -d to restart and roll forward to the new version. The CHANGELOG flags any breaking changes for each release — just take a quick look before upgrading.

Ready to try it?

Open it in your browser — no credit card, no install.

Related

ShareXTelegramLINEWeibo
How to self-host an AI assistant? Enclave in three steps · Enclave