Flowly: Personal AI Agent for Desktop and Mobile

Flowly: Knows your world. Answers to you. | Product Hunt

Knows your world. Answers to you.

346 followers

Knows your world. Answers to you.

346 followers

Visit website

OpenClaw

Flowly is a native AI assistant that takes action across your apps and browser tabs. Summon it as a full chat, from the menubar, or through a notch overlay — one global hotkey away on macOS, Windows, and Linux.

Available for macOS, Windows, Linux. Free during launch.

Overview

Launches3

Reviews

Alternatives

Forum

Team

Awards

More

This is the 3rd launch from Flowly. View more

Flowly

Launching today

A personal AI agent that runs on your desktop and iPhone

Flowly's whole agent core is now open source (Apache-2.0). A personal AI agent that runs on your desktop and iPhone, uses the AI keys you already have, and keeps a private memory of your world that learns and corrects itself. Knows your world. Answers to you.

Free

Launch tags:Android•Productivity•Messaging

Launch Team

Subscribe

Previous Flowly Launches

FlowlyYour personal AI assistant, native to your desktop

Launched on May 4th, 2026

FlowlyYour Personal AI Assistant, One Click Away

Launched on January 30th, 2026

Forum Threads

p/flowly-6•

1mo ago

Flowly v1.4.0 is live! Changelog here.

New Computer Use: Flowly can now act on the Mac directly open apps, click buttons, switch windows, read on-screen text. The bot reads the same semantic UI structure as VoiceOver so it can act on labels you'd say out loud ('the Sign In button in Safari') instead of guessing pixel coordinates. Sandboxed by default; every action visible in the Activity tab.

New Live tool-turn panel: Every assistant message ships a collapsible panel that streams tool calls (file edits, shell, search, computer-use) in real time, with per-tool renderers. The Activity tab's audit view uses the same renderers so history looks identical to live chat.

New In-app file preview: Click a file path the bot mentioned (markdown link or inline code) to open a resizable, syntax-highlighted side panel. Relative paths auto-resolve against common project roots; directories still reveal in Finder.

New Artifacts cloud sync: Canvases, slides, docs, and code sync automatically across signed-in devices. Offline-aware queue, S3-backed previews, 10 MB size cap (up from 500 KB).

New Screen-aware Coach (macOS, opt-in): When you enable it, a native ScreenCaptureKit sidecar shares lossless captures of the window under your cursor with the model alongside audio, so tips can reference what you're actually looking at. ElevenLabs Scribe v2 STT adds [YOU]: / [OTHER]: speaker labels. Dual-Cmd forces a tip mid-session. Notch escalates to always-on-top with a 3-second watchdog.

New Knowledge Graph overhaul: Floating detail panel, click-through entity relationships, in-app entity deletion (cascades to triples), liquid-glass zoom controls, flicker-free node drag.

New What's new modal: First launch after auto-update opens release highlights with a hero matching the website's auth screen and a link to the full changelog.

New Welcome-screen otter mascot (opt-in): Vector otter toggleable from Settings Appearance. Eyes track your cursor while you type, mouth opens pink when you paste, blinks idly.

New Hey Flowly wake word: Production-ready on-device wake-word integration. Talk hands-off when the notch is live without holding Fn.

New Skill library expanded: 30+ new built-in skills covering finance modelling (3-statement-model, DCF, Excel authoring), GitHub workflow (PR review, repo management, code review), design and docs (concept diagrams, Excalidraw, PowerPoint authoring, nano-pdf), and SaaS integrations (Notion, Linear, Airtable, Google Workspace). Browse the full catalogue in Dashboard Skills.

Improvements Sandbox by default: macOS uses sandbox-exec, Linux uses bubblewrap; deny-list profile blocks writes outside the workspace. Master switch in Dashboard Settings. Skill marketplace surfaces per-plugin risk labels.

Improvements Composer attachments: Upload-first flow with per-file status (queued/uploading/ready/failed), 50 MB video uploads, correct serverId/conversationId on every upload.

Improvements Windows / Linux parity: Platform-aware default hotkeys, modifier labels, voice shortcut hints, and smart-pause process detection. Dedicated Windows tray icon.

Improvements Coach quota visibility: Live progress bar in Settings Usage and the sidebar usage popover. Pre-flight gating stops the session cleanly on STT 429.

Improvements Coaching settings is now a floating panel matching the rest of the app's side-panel pattern.

Improvements Dashboard regrouped: AI Tools and Security promoted to top-level groups. Pre-Sonoma macOS gets a friendly capability warning.

Improvements Shared AlertDialog adopts the liquid-glass theme app-wide with softer corners.

Fix Activity tab now scrolls instead of clipping; Radix ScrollArea wrapper repaired.

Fix Tool output rendering is cleaner: stray wrapper markup removed, escape sequences normalised, and excessively long blobs collapse to a short summary by default.

Fix Artifacts: 8 small UX bugs (delete confirm cancel, sort persistence, distinct empty/loading/error states, a11y labels).

Fix Coach screenshots use a quality + cursor-display target that keeps small on-screen text legible to the model.

Fix Granting macOS Accessibility from onboarding registers the global hotkey live; no app restart needed.

Fix Coach Start gated on Flowly AI gateway availability so it doesn't 404 immediately.

Fix Computer Use finds targets more reliably: matches against multiple element attributes (not just the visible label), suggests the closest candidates when an exact match misses, and avoids re-using stale element IDs after a window changes.

Fix Terminal emulators (iTerm2, Terminal, Alacritty, Kitty, Ghostty, Wezterm) get clipboard paste instead of synthetic key events.

Internal Sentry on artifact sync with scope tags. Persistent sync cursor avoids re-uploads after cold restart. Window-hidden poll pause for limits + bot updates. package.json at 1.4.0.

p/flowly-6•

2mo ago

Flowly v1.3.0 is live — plugin marketplace + first featured plugin: Blender control

Since we shipped on PH 6 days ago, we've been heads down on one thing: making Flowly extensible.

What just landed:

p/flowly-6•

2mo ago

Hey 👋 — back with Flowly v2

Hakan from Nocetic here. We launched Flowly v1 on Product Hunt back in January. It was a basic native chat app useful, but honestly a small slice of what we wanted to build.

Since then we shipped what feels like a different product:

A browser agent (companion extension) that doesn't just open URLs but actually drives Google Sheets,

Maps, Gmail, and most other sites fills forms, clicks buttons, navigates flows

A voice coach that lives in the menubar / notch overlay, summoned by a global hotkey

End-to-end encryption by default your conversations leave your device encrypted

Persistent sessions so a long-running task survives navigation (iOS-style continuity on the desktop)

View all

Reviews

No reviews yetBe the first to leave a review for Flowly

Promoted

Maker

📌

Hey Product Hunt — Hakan from Nocetic, the team behind Flowly.

Some of you saw our last launch. Since then I kept circling back to one thing that bugged me: every agent I tried lived in someone else's cloud, was stuck on one model, and forgot who I was the second I closed the tab. Powerful, but never really mine.

So we rebuilt Flowly around three things:

On your machine, your keys. It runs natively on your own computer and your phone, on the AI keys you already pay for — Anthropic, OpenAI, OpenRouter, or a local model, your call. Your data doesn't leave.

A memory of your world. This is the part I care about most. It's not a chat log, it's closer to a model of your world — your people, your projects, the way you work. It tracks what changed and when, and quietly fixes itself when it gets something wrong.

Everywhere you are. Native apps for Mac, Windows, Linux, and iPhone. One agent, in sync.

The big one for this launch: the whole agent core is now open source (Apache 2.0). Read every line, self-host it, point it at any model.

Honest state of things: the memory and the cross-session learning are live and I use them every day, but they're young — they get sharper the more you push them. If something feels off, that's genuinely useful for us.

Two questions I'd love answered in the comments:

1. What's the first thing you'd want your agent to actually remember about trust an agent with your real data?

The big one for this launch: the whole agent core is now open source (Apache 2.0). Read every line, self-host it, point it at any model.

Honest state of things: the memory and the cross-session learning are live and I use them every day, but they're young — they get sharper the more you push them. If something feels off, that's genuinely useful for us.

Two questions I'd love answered in the comments:

1. What's the first thing you'd want your agent to actually remember about you?
2. If you self-host, what would make you trust an agent with your real data?

Thanks for taking a look — we'll be in the comments all day.

— Hakan & the Nocetic team

Report

2d ago