Best of Product Hunt|October 6, 2026

This is a pretty need tool. I have always been a fan of these tools that kind of act as a surface to multiple products. I would recommend expanding to include other tools as more tools outside of Codex and Claude Code will come out and being able to "plug and play" would be cool.

Hey Kamil, what was the biggest challenge or discovery you had when building OpenBot? It could be about anything, from open sourcing the app to coordinating the agents. Congrats on the launch today!

Observability for Agents is a big deal these days. It is something many organizations are trying to solve for but the solutions are limited. This looks pretty cool

Does it also handle marketing funnels or is it purely a sales tool?

Hi all, congrats on the launch! I used to do a lot of work in software accessibility many, many years ago. First, my technical question. Can you tell me more about the implementation? Are you going through the OS level accessibility tree for a Mac or Windows? Or is this just for web-based apps where you're going through the DOM? Or are you doing something totally different by recording mouse movements? Who is your targeted audience that you're designing for? At first I thought this might be an app for someone with low dexterity, but it is unclear to me what the setup or training would look like.

Hi all, congrats on the launch! Can you go into more detail about how the AI agent is trained on your writing style? I saw a comment below that it only takes a few examples. Are these examples you provide (and if so, what sort of examples work best)? Or does it parse your LinkedIn chat / post history for examples? And also, is there a way to give feedback to the AI agent in case it makes repeated mistakes? Also, can you go into more detail about what you mean by "agent-in-the-loop" instead of human-in-the-loop in one of your comments below?

Hi all, congrats on the launch! This is my first time learning about Willow. It sounds like your launch today is a plug-in or new feature to Willow called Willow Knowledge, where you can "export" (or copy & paste) your preferences from your everyday AI agent into Willow. Could I think of Willow Knowledge as agent skills for Willow?

Hi all, I like your approach to learning how to code by small increments. A couple of questions: 1) how do you determine the coding challenges? Have you all looked into "coding katas" that was popular many years ago? 2) what's the progression? Are you going for mastery of the language itself, or is there some sort of choose your own adventure, where the user can choose to learn to code to achieve a specific goal, like shipping a website or mobile app?

Hello Ghostifier! I have a technical implementation question. How do you read only the Gmail email headers? Is this ability through the Gmail API? Congrats on today's launch!

This is great - love that your notes are automatically sorted and summarized. I wish I could have some of these notes shared across devices, otherwise I wouldn't be able to use this as my primary note-taking app.

Howdy! This looks interesting. Is this largely a browser based VM that hosts a developer portal/IDE? Is it for cloud usage or can you use it on your local system or both?

Hey Scumble! First of all, great video! I spend my weekends in Lightroom and PS when I'm not out taking photos. I felt myself participating in that conversation :) Have you received any feedback for tracking token spend or cost? Just thinking out loud, I can spend hours in Lightroom without realizing how much time has gone by.

Hi Pheebs team! I really liked the idea of seeing how often outputs get modified and whether those lead to cost-savings. And also running tests before commits. A few comments / suggestions. 1) Are those metrics shown in the images you have for the Overview? And also, for a given company, is there a way to generate a baseline for a developer's activity that the other developers could follow? for example, maybe you don't need the AI to run and analyze tests after every commit, and only do it before pushing the code? (just thinking out loud for a counter example). Or maybe for a given project, it is better NOT to push back on the code generated by the agent? 2) What do you think of a summary page that shows the recommended steps? You might already have it. I'm only going by the images in the overview.

Congrats on the launch today! I have a couple of questions: Is this just for tasks, and not for actual calendar meetings? In the video, it shows asking Claude to move a 1:1. Is this a task to move the 1:1 or is Claude actually moving the 1:1? Also, why a separate desktop application and not a browser extension? Just curious.