Key points at a glance
- Swappable model layer: both cloud APIs and local Ollama / vLLM can be configured.
- Assign by character / conversation type — sensitive ones go local, complex ones go to the cloud.
- Switch everything to local and turn off external sync to go fully offline.
Step 1: Configure the cloud model APIs
Enter your cloud model API keys in the settings (such as OpenAI, Anthropic, Google, DeepSeek). Cloud models are usually higher quality and quicker to get started with, suited to complex tasks and characters that need top performance.
Step 2: Connect local models (Ollama / vLLM)
Run Ollama or vLLM on your own machine or local network, and enter its local endpoint into Enclave's model configuration. Local model inference never leaves the network, making it suited to privacy-sensitive conversations while also avoiding API costs.
Step 3: Assign models by character / scenario
Assign different models to different characters or conversation types: route sensitive, private conversations to local models, and route tasks that need stronger capability to the cloud. For ultimate privacy, switch every model to local and turn off real-world sync, and the whole system goes fully offline.
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.