Tap to begin. Talk for as long as you like.
 
What I'm hearing
Recent rambles
Pick a page to read.

Your brain.

A living model of what you've told me. Growing with every ramble. Trained on a GPU when you're ready.
Pages absorbed
Connections
Pending since last train
Last trained
never
How it works. When you train, every wiki page is turned into 3–4 Q&A pairs in your AI's voice, sent to a GPU on RunPod, fine-tuned as a small LoRA adapter, and pushed to a private Hugging Face repo. ~5 minutes, ~$0.04. The brain pulses while it learns.

Chat with the version of you that's been baked.

checking…
What do you want to ask the wiki?
your wiki is thinking
Hear it spoken

Settings

Stored only in this browser. Never sent anywhere except the providers below.

Where your data lives.
Always: in this browser's localStorage (you.wiki, you.rambles, you.cfg).
Optional, recommended: connect a folder on your disk and your wiki will mirror as .md files. Then it works with Obsidian, git, iCloud, any text editor — natively.
Not connected. Wiki lives only in this browser.
The voice your AI speaks in. Default is Brian — gentle, mature, narrative. Anthropic + ElevenLabs API keys live as Vercel env vars and never reach the browser.