upcoming ai innovation

mainline intelligence

is coming — the new wave of pyx.

mi is our next ai platform — the umbrella for breakthrough systems that push past today’s assistants into realtime, industrial-grade intelligence. same mainline promise: premium experiences, free to reach.

try pyx assistant about the beta mi moderator mailing list

coming soon

beta · api preview

mainline artificial realtime instant intelligence (marii)

instant when it matters. realtime when the world moves. this is mainline’s leap into ai that keeps up — responses that feel native to the moment, built for creators and players who will not wait on a spinner.

instant responses. real data. all free.

first public beta: pyx assistant (powered by marii) — local-first in the browser, no cloud llm. extremely early and still being improved. read the honest overview: about pyx assistant. browse all betas at /betas.

related: announcer — live mlb play-by-play with game-scoped marii ask.

coming soon

mainline conversational intelligence (mci)

the industrial evolution of pyx — conversation engineered for serious work. deeper context, stronger reliability, and studio-grade dialogue for teams and products that need ai they can actually ship with.

mi mailing list

drop your email for mi updates — moderator tips, marii/mci drops, and the occasional “we shipped something weird.”

no, we won’t make it ads. we’ve already done enough crimes against your attention span.

welcome mail comes from no-reply@pixelplaceofficial.com · replies hit support

mi moderator

live now. hit the path with your text. you get something like {"appropriate":false,"score":"700"}. score is 0–1000. default threshold is 700.

get https://mainline-intelligence.web.app/moderator/check/<text>

phrase

threshold

value

lower = stricter. higher = chill.

// response shows up here

add it to your game

one get. look at appropriate, or compare score to your own threshold.

url-encode the text and call /moderator/check/<text>
optional: ?threshold=700 so the api sets appropriate for you
if appropriate is false, block or ask them to rephrase
tune the threshold per mode

fetch("https://mainline-intelligence.web.app/moderator/check/" + encodeURIComponent(text) + "?threshold=700")
  .then(async (r) => {
    const raw = await r.text();
    try { return JSON.parse(raw); }
    catch { throw new Error(r.status + " " + raw.slice(0, 80)); }
  })
  .then((data) => {
    // { "appropriate": false, "score": "700" }
    if (!data.appropriate) {
      // block or rewrite
    }
  });

dev’s corner

hooks, trainers, and studio tools for pyx + mi. poke around, wire stuff up, or jump the mci waitlist.

mi moderator try-it live word check · /moderator/check/<text>
pyx studio talk, code, speak, pyxel, workspace — the full creative stack
mainline intelligence training traffic-light captcha that helps train mi
trainer / dev workshop sign in for labeling, traffic analyzer, workshop tools
pyx assistant local-first marii beta · voice, sports, weather, math
about pyx assistant what it is / isn’t — short write-up
pyx betas assistant + announcer and other early surfaces
pyx talk conversational pyx in the browser
pyx code code assist + agent patches
pyx speak text → voice, including native pyx tacotron
downloads desktop builds and release bits
/api/health api pulse check
/api/score legacy score health (post {"text"} for full scores)
github · pyx-ai source, issues, and how the stack is wired

mci / mi list

want early peeks at mci and the rest of the wave? join the mi mailing list — same inbox, zero ad billboards.