Lyto

The context-loss problem between tools is the thing that broke me too. I'd start something in Claude, jump to my own product to test it, then back to Claude and it had no memory of why we started. Ended up writing my own context notes by hand like an old engineer keeping a logbook.The WhatsApp/Telegram angle is smart. Most "AI assistants" still assume you're sitting at a desktop. Curious where it breaks down is the bottleneck the model losing track on longer threads, or is it the user not knowing what to ask for once the agent has full context?

The WhatsApp and Telegram integration is a clever touch!!

How do you decide what information is worth remembering versus what should be forgotten? That balance seems like one of the hardest problems for long-running AI agent in my humble opinion.. ☺️

The context-loss problem you describe in the intro is the exact thing I keep hitting building voice AI agents. The moment you move across surfaces, the assistant forgets what it was mid-way through. Curious how Lyto holds that state when it acts inside Gmail or Sheets versus a normal tab. And for the harder-to-undo actions like sending an email or editing a doc, does it confirm with the user first or act and let you roll back?

one agent across browser, tools, and messages is ambitious, that's a lot of surface area to keep consistent. what's been the trickiest part so far, getting it to actually act vs just summarizing/suggesting stuff.

Hey, how does Lyto handle the case where the source data or target workflow is inconsistent instead of clean?

Good to hear the gate is on mutative actions. The case that bit me building browser automation: a Gmail send is easy to intercept because there is a discrete click to gate, but Sheets and Docs commit on blur, there is no submit event. So a cell edit is already live by the time you would show a preview. Do you stage those edits before writing back, or is the confirm only on actions with an explicit send button?

One agent that follows me across the browser, my tools, and my messages is a smart angle, most assistants make me come to them in one tab.

That’s a fantastic idea!Did the inspiration come from a tedious task you personally had to deal with?Or was it based on requests from users?

The browser-as-agent-surface bet is the right one. I have spent a lot of time driving real pages with DOM clicks, so the part I keep landing on is the write side. Reading tabs is low stakes, but once it fills and submits forms in Gmail or Sheets, one misread intent sends the email or overwrites a cell. Is there a confirmation gate on mutative actions, or a preview before it commits? That boundary is what decides whether I would let it touch my inbox.

The Google Docs + Gmail + Sheets integrations are what make this practical - those are the three apps most people actually live in, so hitting them first was the right call. Full DOM interaction is powerful but also where browser agents usually hit walls. Two things I'm curious about: how does it handle sites heavy on shadow DOM or cross-origin iframes? That's typically where this approach breaks down. And is agent context session-persistent, or does it lose memory of what it just did when you close and reopen Chrome?

The persistent workflow memory across tabs and tools is the part that stands out - that context loss is exactly what breaks when you bounce between ChatGPT and your actual tabs. Where does that memory actually live: locally in the extension, or synced to your backend (matters a lot once it is reading Gmail and Sheets)? And when it acts on a page, is the DOM automation running locally in my browser while only the reasoning is hosted, or does the page content get shipped server-side on each step?

Hey Product Hunt 👋

We’re the team behind Lyto.

This started from a problem that drove us crazy. Every time you work, you’re jumping between ChatGPT, your tabs, your docs, your email, and the second you switch, your AI forgets everything you were doing. You’re constantly re-explaining context just to get one thing done.

So we built Lyto. It’s an AI agent that lives in your browser, remembers your entire workflow, and actually does the work instead of just talking about it. It reads your pages, fills your forms, builds your spreadsheets and reports, and connects to the tools you already use like Gmail, Slack, Sheets, and GitHub.

The feature people seem to love most: you can text Lyto from WhatsApp or Telegram, ask it to build a report with graphs, and it sends the finished file straight to any contact. No laptop needed.

It started as a browser extension and honestly looked nothing like it does now. We pivoted hard based on what real users and teams actually needed, and somewhere along the way real companies started using it to run their workflows.

We’d genuinely love your honest feedback. The good, the broken, all of it. That’s the only thing that makes this better.

Try it and tell us what you think 🙏