Tripplet

Tripplet is one workspace for chat, code and research — four specialised models bound not by a single provider or a single trick, but by the work you actually bring them.

Ask anything

Start the conversation here. It follows you in. 

Free to start · No account required · Your message carries into the chat

Four models

One conversation, four kinds of thinking. Switch mid-sentence and your context comes with you. 

Astro reaches for the hardest problems, Taipei works through the ones that need structure, Majuli keeps pace with an ordinary day, and Suzhou answers before you have finished reading the question. Every one of them streams token by token, runs real code, searches the live web, and remembers what mattered last time.

Studio-grade tooling for people who actually build. 
Built for real work. Powered by four minds. 

Your workspace, thinking.

Live web search. 01

  • Fresh results pulled into context as you ask
  • Answers that reflect today, not a training cutoff
  • Cited sources you can open and check
  • Falls back to keyless search when a key is absent
See what it can do

Real code execution. 02

  • Python runs in a sandboxed interpreter, not a guess
  • Real output and real errors, shown as they happen
  • A full in-browser Linux VM when you need a shell
Open the Code workspace

Memory & connectors. 03

  • Durable memory that carries across conversations
  • Search your own past chats from inside a new one
  • GitHub, Gmail and Notion, scoped to your account
Browse the integrations

The lineup

Four models. One conversation away.

Every model in Tripplet is tuned for a different kind of thinking. Switch between them mid-conversation — your context comes along.

astro-5Flagship

Astro 5.2

Our most capable model — deep reasoning, agentic tool use, and full code pipelines through Astro 5.2 Code.

taipei4-1Reasoning

Taipei 4.1

Structured thinking for research, analysis, and multi-step problems that deserve more than a first guess.

majuli4-1Everyday

Majuli 4.1

The balanced daily driver — fast enough to keep up, thoughtful enough to be worth asking.

suzhou4-1Instant

Suzhou 4.1

Light and immediate. Free for guests, no account required — start a conversation in one click.

Modes & tones

Shape how it thinks — and how it talks.

Modes change the model's approach; tones change its voice. Stack them however the moment calls for.

think

Think

Slows the model down for careful, low-temperature reasoning when precision matters.

deep-research

Deep research

A longer leash and a bigger budget — thorough, multi-angle answers for hard questions.

web-search

Web search

Live results woven into the conversation, cited and current.

study

Study

Explains instead of solves — guides you to the answer so it sticks.

Tones:formalconcisedetailedminimal

Connectors

Bring your own tools.

Link the apps you already live in, and Tripplet can read and act on them — issues, mail, docs — scoped to your account, revocable any time.

GitHubGmailNotionand more

For developers

Streamed, not spooled.

Every response is server-sent events from the first token. Build on the same streaming API the Tripplet interface runs on — plus an MCP server and OAuth for your own agents.

Get an account
stream.ts
const res = await fetch('/api/chat', {
  method: 'POST',
  body: JSON.stringify({
    model: 'astro-5',
    messages: [{ role: 'user', content: 'Explain quines.' }],
  }),
});

// Server-sent events — tokens as they're generated
for await (const chunk of readSSE(res.body)) {
  render(chunk.delta);
}

Triplepedia

A knowledge base that grows with you.

Articles you can read, extend, and pull straight into a conversation — Tripplet's collective memory, one tab away.

Browse Triplepedia
Stay curious. 

Free to start — no card, no setup. Guests get Suzhou 4.1 instantly; an account unlocks the full lineup.

Tripplet — AI that works the way you think