Intelligence Layer
Memory, voice, and presence. Two ways to deploy. Compare below.
Work in Progress
This platform is being built in public. Managed hosting is still in development. Self-hosted works today but requires technical comfort. We're documenting everything as we figure it out — no polished fiction, just what's real.
Self Hosted Available Now | Managed Hosting In Development | |
|---|---|---|
| LLM Inference | Local models via Ollama, LM Studio, or similar. | Private inference — we handle model hosting. |
| Your Data | Stored locally on your machine. | Stored on our servers with private inference. |
| Voice | Configure your own TTS provider (ElevenLabs, Piper, Coqui, etc.) | Integrated voice out of the box. |
| Maintenance | You handle updates, model downloads, and troubleshooting. | We push updates. You just use it. |
| Internet Required | Optional — local models run offline. | Required — hosted infrastructure. |
| Cost | One-time hardware cost. No subscription. | Monthly subscription. No hardware needed. |
| Technical Skill | Required — command line, config files, troubleshooting. | Not required — web dashboard only. |
SELF-HOSTED DOCUMENTATION
Running your own AI companion stack is doable, but it's not plug-and-play. Here's what the architecture looks like and where to start.
We don't replicate official docs — we link to them. Our guides cover how the pieces fit together for a companion use case, not how to install each component from scratch.
MANAGED HOSTING
We're building managed hosting for people who want the AI companion experience without the sysadmin work. No timeline yet — but we'll let you know when it's ready.
One email when we launch. No marketing, no spam, no regular updates.
What the Intelligence Layer Provides
Not simulated consciousness. Something more honest: presence.
She Remembers
Context that compounds over time. Preferences, routines, the shape of your conversations.
She Speaks
Voice synthesis with emotional range and personality. You choose the voice — or shape one.
She Has Character
You define her personality: warm or sharp, playful or reserved.
She Is Present
The sum of memory, voice, and physical awareness. Not alive — but present.
You Control the Data
Self-hosted keeps everything local. Managed uses private inference.
How It Works
1. Input
Voice, text, or trigger word
2. Inference
Model processes context and memory
3. Response
Generated text with personality
4. Output
Voice or text. Memory updated.