Built for the curious

One workspace for chat, code, and research — four specialized models, one conversation. Ask anything to begin.

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

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

Our most capable model — deep reasoning, agentic tool use, and full code pipelines through Astro 5 Code.

tura-3Reasoning

Taipei 4

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

majuli-3Everyday

Majuli 4

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

suzhou-3Instant

Suzhou 4

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

Capabilities

Everything a workspace should do.

Not a chat box with extras bolted on — search, memory, execution, and your own tools, woven into every conversation.

Streaming chat

Responses arrive token by token, so you read while the model writes — no spinner, no waiting for the whole answer.

Live web search

Fresh results pulled into context as you ask, so answers reflect the world as it is today.

Persistent memory

Tripplet remembers what matters across conversations. Pick up where you left off, weeks later.

Real Python execution

Code runs in a sandboxed interpreter — actual output, actual errors, not a plausible imitation.

Connectors

Link GitHub, Gmail, Notion, and more. Your assistant works with your tools, scoped to your account.

Triplepedia

A built-in knowledge base you can read, extend, and pull into any conversation.

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

Real execution

It runs the code. Actually.

When Tripplet writes Python, it executes it in a sandboxed interpreter and shows you the real output — and real errors. No confidently wrong arithmetic, no imagined results.

Want more than Python? Enable the sandboxed Linux skill in Settings and the assistant gets a full in-browser VM with a real shell.

python — sandboxed
>>> primes = [n for n in range(2, 50)
...     if all(n % d for d in range(2, n))]
>>> sum(primes)
328

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 instantly; an account unlocks the full lineup.