Key points at a glance
- Ollama lets you run open-source large models on your own machine, with inference never leaving the network.
- On top of the model, Enclave fills in memory, proactivity, multiple experts, and deliverables.
- Combine the two = a privacy-first AI companion whose data never leaves the machine.
Why run an AI companion locally
AI companionship involves a lot of private conversation. Entrust it to the cloud and privacy rests only on terms; run the model locally and inference happens on your own machine, with data never leaving the network — the thing privacy-first users value most. Ollama makes running open-source large models locally simple.
What Ollama handles, and what Enclave handles
Ollama is a model runtime that efficiently runs models locally, but it doesn't provide memory, proactivity, or multiple characters on its own. Enclave is the world built on top of the model: long-term memory, proactive follow-ups, multiple expert residents, and real deliverables. Use Ollama as Enclave's local model backend, and the two complement each other into a complete experience.
How to set it up
First, run Ollama locally and pull your model, then self-host Enclave and point its model backend at your local Ollama endpoint — see the self-hosting tutorial and hybrid model setup for details. Go fully local and turn off external sync, and you'll have a completely offline AI companion world whose data stays on your own machine.
FAQ
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.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).
Ready to try it?
Open it in your browser — no credit card, no install.