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

Wink

The harness for self-improving frontier agents.

Talk to one orchestrator and it spawns Claude Code, Codex, Grok, Gemini and Muse agents in real terminals. When you correct it, it writes the lesson down, and on code it adds a check that fails if the mistake comes back. Your decisions are saved in your own words, with dates. Check in from your phone. Free, open source, Windows. Runs on the subscriptions you already pay for, no API keys.

Top comment

Hi Product Hunt, I'm Edward.

I started building Wink because I was the copy-paste middleman. I ran Claude Code and Codex in tmux panes, one per bot, and carried every message between my planning chat and each terminal myself. For memory, I kept an Obsidian second brain and made every new chat read my md files first.

Now I talk to one orchestrator. It spawns Claude Code, Codex, Grok, Gemini and Muse agents in real terminals, on the subscriptions I already pay for. When I correct it, it writes the lesson down, and on code it adds a check that fails if the same mistake comes back. I don't keep those md files by hand anymore.

I like terminals because they're fast. I can start Claude Code, type the task and be out the door. That's the speed I want Wink to have.

Why "Wink": in the blink of an eye, the bot spawns its workers and the job is done.

It's free and open source, Windows only for now, and the installer isn't signed yet, so Windows will warn you. If you have a few minutes, give it a try and tell me what you like and what you don't. If you like an idea, take it.

About Wink on Product Hunt

“The harness for self-improving frontier agents.”

Wink was submitted on Product Hunt and earned 4 upvotes and 1 comments, placing #81 on the daily leaderboard. Talk to one orchestrator and it spawns Claude Code, Codex, Grok, Gemini and Muse agents in real terminals. When you correct it, it writes the lesson down, and on code it adds a check that fails if the mistake comes back. Your decisions are saved in your own words, with dates. Check in from your phone. Free, open source, Windows. Runs on the subscriptions you already pay for, no API keys.

On the analytics side, Wink competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Wink performed against the three products that launched closest to it on the same day.

Who hunted Wink?

Wink was hunted by Edward Yi. 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 Wink including community comment highlights and product details, visit the product overview.