Flagship demo
AI Assistant Chatbot
One engine, many professions. Pick a profile and tone, keep recent chats in your browser, and watch context compaction happen live when conversations get long.
Without a key, you can watch scripted sample conversations. Add your key below for live AI: it stays in your browser for this session only.
⚡ Run it live with your own API key no key set
Your key is held in memory for this session (kept for this tab only if you tick the box) and sent only to the provider you choose, directly from your browser. This site has no backend server — you can confirm it in your browser's Network tab: requests go only to the provider, never to this site. Live runs use small, fast models with hard token caps; a typical run costs well under $0.01, billed to your own account.
Honest limits: no website can protect a key from a compromised browser or malicious extension. Use a key with a spending cap, and revoke it after playing if you like.
How it’s engineered
- One tested conversation engine; each profession is just a system-prompt preset, so new verticals cost a config entry, not a rebuild.
- When the history exceeds its token budget, older turns are folded into a rolling summary and the UI shows the compaction event, the same technique that keeps production context windows flat.
- Recent chats live in your browser localStorage. In live mode, messages go directly from your browser to your chosen provider; there is no middleman server.
- Live mode pins small, fast models with hard token caps to protect your key; a token meter keeps usage visible.