This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Harf
Say it. Harf does it. Voice agent for your Mac apps
Harf is a voice-first AI agent for Mac. Say "Hey Harf" and give a task in your own words. Harf uses what's on your screen as context and acts inside the app: a dark version of a Figma screen, a photo edited in Photoshop, an email reply drafted from the open thread. You review the result before anything goes out. Not dictation, action.
Hey Product Hunt, I'm Ram, part of the team building Harf with our founder, Nilmani Kumar.
Every task on a Mac means switching windows and re-explaining context. Harf lets you say what you need once, and does it inside the app you're already in.
In the video, Harf turns a Figma checkout screen dark and edits a portrait in Photoshop, from one spoken sentence each. Harf is built so that anything consequential (sending, deleting, buying, publishing) waits for your OK.
On privacy: speech-to-text runs on your Mac, and Harf only reads your screen when you give it a task. Reasoning uses Claude by Anthropic. The full data-flow and retention policy will be published on theharf.com before early access opens.
Harf is in private demo right now. Join early access at theharf.com, and tell us the first task you'd hand Harf: those answers decide which apps it learns next. Nilmani and I are here all day.
About Harf on Product Hunt
“Say it. Harf does it. Voice agent for your Mac apps”
Harf was submitted on Product Hunt and earned 2 upvotes and 2 comments, placing #156 on the daily leaderboard. Harf is a voice-first AI agent for Mac. Say "Hey Harf" and give a task in your own words. Harf uses what's on your screen as context and acts inside the app: a dark version of a Figma screen, a photo edited in Photoshop, an email reply drafted from the open thread. You review the result before anything goes out. Not dictation, action.
On the analytics side, Harf competes within Mac, Productivity and Artificial Intelligence — topics that collectively have 1.3M followers on Product Hunt. The dashboard above tracks how Harf performed against the three products that launched closest to it on the same day.
Who hunted Harf?
Harf was hunted by Ram Sarjal. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Harf including community comment highlights and product details, visit the product overview.
Ram Sarjal
Hey Product Hunt, I'm Ram, part of the team building Harf with our founder, Nilmani Kumar.
Every task on a Mac means switching windows and re-explaining context. Harf lets you say what you need once, and does it inside the app you're already in.
In the video, Harf turns a Figma checkout screen dark and edits a portrait in Photoshop, from one spoken sentence each. Harf is built so that anything consequential (sending, deleting, buying, publishing) waits for your OK.
On privacy: speech-to-text runs on your Mac, and Harf only reads your screen when you give it a task. Reasoning uses Claude by Anthropic. The full data-flow and retention policy will be published on theharf.com before early access opens.
Harf is in private demo right now. Join early access at theharf.com, and tell us the first task you'd hand Harf: those answers decide which apps it learns next. Nilmani and I are here all day.