Key points at a glance
- Janitor AI is cloud-based, closed-source, and focused on roleplay; Enclave is open source and self-hostable, with data stored only on your machine.
- Enclave's structured long-term memory can be managed entry by entry, so characters still remember you months later.
- Enclave is more than chat: multiple experts, proactive follow-ups, and the ability to produce real documents.
Side-by-side comparison
| Dimension | Enclave | Janitor AI |
|---|---|---|
| Product positioning | A private assistant world for both companionship and getting things done | Open-ended roleplay chat |
| Open source & self-hosting | MIT open source, self-hostable | Closed-source, cloud-only |
| Long-term memory | Structured long-term memory, manageable entry by entry | Primarily session context |
| Data control | Self-hosted, stored only locally, exportable / deletable | Data stored in the platform's cloud |
| Model choice | Swappable: OpenAI / Anthropic / local Ollama and more | Use platform models or bring your own key |
| Scope of capabilities | Multiple experts, proactive follow-ups, real document deliverables | Focused on character conversation |
How to choose
If what you want is cloud-based, ready-to-play open-ended roleplay, Janitor AI is quick to pick up; if you want an open-source world where the data is yours, characters remember you over the long term, and they can proactively get things done for you, Enclave is the better fit.
FAQ
Can multiple AI characters do group chat / roleplay together in Enclave?
Yes. You can bring multiple AI characters into the same group, each with their own personality, memory, and relationships with one another (friends, rivals, mentor-and-student); they'll respond to, discuss, and even argue with each other. You can act as the director driving the plot, or join the conversation directly — perfect for TRPG, murder-mystery games, and creative collaboration.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.Is Enclave open source? What license does it use?
Yes. The entire Enclave monorepo is open source on GitHub under the MIT license — free to audit, modify, and use commercially. Any promise that we won't misuse your data is something you can verify by reading the code yourself, instead of just having to take it on faith.
Ready to try it?
Open it in your browser — no credit card, no install.