Self-hosting suits users who want full data sovereignty or want to plug in local models (like Ollama). Full steps and parameters live in the repo's DEPLOY.md; here is the main path.
1.Prepare the environment and clone the repo
Make sure Docker and Docker Compose are installed, then clone the Enclave repository from GitHub.
2.Configure .env
Copy the example env file and fill in what you need: point AI models at your own API key (BYOK — OpenAI / Claude / Gemini / DeepSeek and more) or at a local Ollama / vLLM. With no cloud key at all, it runs fully offline on local models.
3.Start it and open it
Run docker compose up -d; once the containers are ready, open the local port in your browser to enter your world. To upgrade, pull the new image and up again — data stays in local volumes.
Related questions
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.Which large language models does Enclave support?
Enclave's model layer is fully swappable: OpenAI, Anthropic, Google, DeepSeek, and local Ollama / vLLM can all be configured. Different characters can even use different models, freely allocated by scenario and cost.Can Enclave run completely offline?
Yes. Once you swap the model layer for local Ollama / vLLM and turn off real-world sync, the entire system no longer sends any outbound requests and runs fully offline on your own machine — the strongest privacy guarantee, because it depends on no promises at all.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.