MDriven Assistant · v2.0

The MDriven chat widget,
rebuilt clean.

One AI assistant, MDriven colours, no mode picker and no forms to fill in. Answers stream in from the Brain API with real citations. Open it from the bubble in the bottom-right corner to try it out.

Streams as it writes

Sources land in about 100 ms, the first words just under a second, so nobody watches a spinner for ten seconds. Stop any answer mid-flight.

Real citations

Inline [1] markers become links to the exact wiki page or video the claim came from, listed as chips under every answer.

Safe by default

Every token is HTML-escaped before formatting, links are restricted to http/https, and only the public-tier key ever reaches the page.

Fits every screen

Full-bleed on phones, chrome-trimmed on short laptops and landscape, roomier on large displays — resize this page and watch it adapt.

Embed it

One tag, anywhere on the page. No dependencies, no iframe, no CSS bleed into the host site.

<!-- MDriven Assistant -->
<script src="https://chat.mdriven.net/mdriven-loader.js" defer></script>

Brand palette

Taken directly from the tokens published on mdriven.net.

Brand#f6821f
Brand light#ffb135
Brand dark#bf4b0f
Navy#112b3c
Navy deep#09161e
Blue#1a50ad

Where answers come from

The widget calls the Brain API directly from the browser on the public tier.

POST https://brain.demotwo.site/ask/stream
Authorization: Bearer fTKeUoHu…   // public tier, safe in page source
body: {"q": "…", "k": 6}

event: sources   ~100 ms  -> citation chips
event: delta     ~0.9-1.7 s -> appended verbatim
event: done      4.5-11 s (cached repeats: ~3 ms)

Public tier caps k at 8, disables deep, and allows 30 questions per 5 minutes per IP — a 429 is shown as a plain “please wait a minute” message. The API keeps no history, so short follow-ups carry the previous question forward automatically.

Press Esc to close the panel · Enter sends · Shift + Enter adds a line.