Tripplet — AI that works the way you think
Built for the curious<br>One workspace for chat, code, and research — four specialized models, one conversation. Ask anything to begin.
BrowseReasonCode<br>Astro 5
Free to start · No account required · Your message carries into the chat
The lineup<br>Four models. One conversation away.<br>Every model in Tripplet is tuned for a different kind of thinking. Switch between them mid-conversation — your context comes along.
astro-5Flagship<br>Astro 5<br>Our most capable model — deep reasoning, agentic tool use, and full code pipelines through Astro 5 Code.
tura-3Reasoning<br>Taipei 4<br>Structured thinking for research, analysis, and multi-step problems that deserve more than a first guess.
majuli-3Everyday<br>Majuli 4<br>The balanced daily driver — fast enough to keep up, thoughtful enough to be worth asking.
suzhou-3Instant<br>Suzhou 4<br>Light and immediate. Free for guests, no account required — start a conversation in one click.
Capabilities<br>Everything a workspace should do.<br>Not a chat box with extras bolted on — search, memory, execution, and your own tools, woven into every conversation.
Streaming chat<br>Responses arrive token by token, so you read while the model writes — no spinner, no waiting for the whole answer.
Live web search<br>Fresh results pulled into context as you ask, so answers reflect the world as it is today.
Persistent memory<br>Tripplet remembers what matters across conversations. Pick up where you left off, weeks later.
Real Python execution<br>Code runs in a sandboxed interpreter — actual output, actual errors, not a plausible imitation.
Connectors<br>Link GitHub, Gmail, Notion, and more. Your assistant works with your tools, scoped to your account.
Triplepedia<br>A built-in knowledge base you can read, extend, and pull into any conversation.
Modes & tones<br>Shape how it thinks — and how it talks.<br>Modes change the model's approach; tones change its voice. Stack them however the moment calls for.
think<br>Think<br>Slows the model down for careful, low-temperature reasoning when precision matters.
deep-research<br>Deep research<br>A longer leash and a bigger budget — thorough, multi-angle answers for hard questions.
web-search<br>Web search<br>Live results woven into the conversation, cited and current.
study<br>Study<br>Explains instead of solves — guides you to the answer so it sticks.
Tones:formalconcisedetailedminimal
Real execution<br>It runs the code. Actually.<br>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<br>>>> primes = [n for n in range(2, 50)<br>... if all(n % d for d in range(2, n))]<br>>>> sum(primes)<br>328
Connectors<br>Bring your own tools.<br>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<br>Streamed, not spooled.<br>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<br>stream.ts<br>const res = await fetch('/api/chat', {<br>method: 'POST',<br>body: JSON.stringify({<br>model: 'astro-5',<br>messages: [{ role: 'user', content: 'Explain quines.' }],<br>}),<br>});
// Server-sent events — tokens as they're generated<br>for await (const chunk of readSSE(res.body)) {<br>render(chunk.delta);
Triplepedia<br>A knowledge base that grows with you.<br>Articles you can read, extend, and pull straight into a conversation — Tripplet's collective memory, one tab away.
Browse Triplepedia
Stay curious.<br>Free to start — no card, no setup. Guests get Suzhou 4 instantly; an account unlocks the full lineup.<br>Create an accountRead the manifesto
© 2026 Tripplet