A single-character AI can't hold up a world
Write a story with a single AI and over time characters "forget," personalities drift, and settings stop matching; getting several characters to perform together is even harder — traditional tools lack a world where characters share memory and relationships.
Hand your characters to a world with state
Enclave gives each character a full persona, memory, and a web of relationships; in group chats they remember the plot they've shared and consider what others just said. You can "silently" advance the plot and set the scene, or step in to play a part, switching anytime between director and participant.
Side-by-side comparison
| Dimension | Enclave | SillyTavern |
|---|---|---|
| Product positioning | An out-of-the-box private assistant world | A highly customizable roleplay chat frontend; bring your own backend |
| Open source & self-hosting | MIT open source, self-hostable | Open source, self-hostable (self-hosted frontend) |
| Long-term memory | Built-in structured long-term memory, ready out of the box | Configure it yourself via extensions / vector plugins |
| Proactivity | Experts proactively remind and message you — measured, never spammy | Primarily passive conversation |
| Multiple characters & relationships | Multiple experts and a relationship network, with group chats orchestrated by the system | Supports multiple characters, but requires manual orchestration |
| Real deliverables | Can directly produce PPT / Word / Excel | Focused on roleplay and conversation |
How it works in practice
Characters don't forget
Personas, experiences, and relationships are stored in a structured way, staying consistent even across a long work.
Relationships drive the plot
Friends, rivals, lovers — relationships between characters genuinely shape how they interact and clash.
Director mode
Set the backdrop, advance the plot, have a character do something — without always being the protagonist yourself.
Shared world state
Time, place, and weather are shared across the group, and the story moves forward along a consistent virtual timeline.
FAQ
Is it good for long novels / serials?
Yes. Structured memory is designed for exactly this long-term consistency — characters still remember early setups and foreshadowing dozens of chapters later, and you can view and edit any memory entry to correct course.Are there limits on content?
The bounds depend on the model you connect and your own settings. Enclave connects models via BYOK and can be self-hosted, so you control more of the creative latitude; please follow the terms of the model in question and your local laws.Can it run TRPGs / murder mysteries?
Yes. Each NPC is an independent character with relationships to the others; you run the session as host and the AIs react according to their personas.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.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.