Skip to main content
Enclave
Self-hosted / privacy

Ollama alternative · Self-hosted / privacy

Enclave and Ollama solve problems at different layers. Ollama makes it easy to run open-source large models on your own machine—it's a "model runtime." Enclave is an assistant world built on top of models—long-term memory, proactive follow-ups, multiple experts, real document deliverables. The two are actually complementary: you can have Enclave use Ollama as a local model backend, enjoying both the privacy of local inference and a complete assistant experience.

The cost of handing your private conversations to the cloud

Mainstream AI chat products store your conversations in the cloud and feed them into future training. Even when the ToS says "we won't," you have no way to verify it yourself. The moment your account gets locked, the platform shuts down, or compliance rules shift, those chats are no longer in your hands.

The entire stack is open-source — running it yourself is the strongest privacy promise there is

The entire Enclave monorepo lives on GitHub under MIT — audit it, modify it, fork it. A single docker compose spins up your own instance with API, frontend, database, and vector index all running locally. The model layer mixes cloud APIs and local Ollama / vLLM however you want — you decide which model handles which kind of conversation.

Side-by-side comparison

DimensionEnclaveOllama
The layer it addressesAn assistant world on top of modelsA local model runtime
Long-term memoryBuilt-in structured long-term memoryNot applicable (provides inference only)
ProactivityExperts proactively remind and follow upNot applicable
Multiple characters and deliverablesMultiple experts, group chats, can produce PPT / Word / ExcelOnly a model inference interface
How the two relateCan be plugged in as a local model backendCan serve as one of Enclave's model sources
PrivacySelf-hosted + local models can be fully offlineRuns locally, offline by nature

How it works in practice

  • Fully open-source code

    MIT-licensed with no binary black boxes — every "we won't touch your data" promise is something you can audit yourself.

  • Three-minute Docker deployment

    clone → cp .env → docker compose up. The README spells out the whole flow up top — anyone can spin it up.

  • Fully swappable models

    Plug in OpenAI, Anthropic, Google, DeepSeek, or local Ollama / vLLM — different characters can even run on different models.

  • Data you can back up and delete

    Self-hosted, the data itself is files on your disk: copying is backing up, taking them along is migrating, deleting is truly deleting — no "copies you can't remove".

FAQ

  • How hard is self-hosting?
    If you've used docker compose, it's about as hard as running any other web service. The README's "three-minute deploy" flow is real — clone, edit .env, start the services. Three steps.
  • Can it run fully offline?
    Yes. Swap the model layer for local Ollama or vLLM, turn off real-world sync, and the entire system stops making any outbound request.
  • Can a self-hosted instance still get the official feature updates?
    Run git pull + docker compose up -d to roll forward to the latest version. The CHANGELOG flags breaking changes for every release.
  • 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.
  • 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).
  • Is my conversation data safe? Will it be used for training?
    In self-hosted mode, your conversations live only on your own drive — they never leave your machine and are never used by any third party for training. The model layer can connect to cloud APIs like OpenAI and Anthropic, or be swapped for local Ollama / vLLM to run fully offline; you decide which kind of conversation goes to which model.

Ready to try it?

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

Related

ShareXTelegramLINEWeibo
Ollama alternative · Self-hosted / privacy · Enclave