When your fitness app shows "Recovery Score: 72", do you know how it got that number?

With Whoop, Oura, Fitbit you don't. Black box. Can't audit it, can't tune it, can't verify it works for your users.

And it matters more than you'd think:

We built AI that's constrained to your component library - so it can't go off-brand

Something we kept seeing across every enterprise team we work with: AI design tools generate fast, then the cleanup takes longer than building from scratch.

The pattern is always the same. The AI generates a beautiful dashboard. Everyone's impressed. Then someone looks closely. Wrong button variant. Spacing doesn't match the system. The card uses a shadow you deprecated months ago. The loading state doesn't exist. A developer receives it and rebuilds everything using the real components anyway.

The generation was fast. The aftermath was expensive.

You now have full control over your entries, without losing what matters.

What's new:
Edit your entries anytime
Move entries to trash instead of deleting them permanently
Restore deleted entries within a recovery window
Better control and safety for your writing
New hint to discover long-press options

We're excited to announce v0.10.21 with several major features and improvements.

Voice to Text (Preview) Transcribe voice input in the Agent sidebar entirely on-device. Your voice data never leaves your machine, giving you complete privacy and control over your transcriptions.

Hey Product Hunt!

One week since launch, and we're incredibly grateful for all the support. Thank you to everyone who upvoted, tried the tool, and shared feedback - it means the world to us. We've been heads-down shipping since day one. Here's what landed in just 7 days:

• Multi-platform publishing - Publish directly to Instagram, Threads, and X - not just LinkedIn anymore

• Guided Mode - The AI walks you through the right questions before generating, so your carousels are better from the start

• Built-in web research - Paste any URL (blog post, article, landing page) and the AI reads it to create your carousel

• Better generation & editing quality - Overall improvements to how carousels are generated and edited

• Bug fixes - We listened and fixed several issues reported by our users

We're building this for you, and we mean it. Your feedback drives every decision we make.

Hey Product Hunt community

It s been a week since we launched Ovren - and I just want to say a genuine thank you.

We built Ovren because every team has backlog work that never makes it into a sprint.
Not more ideas. Not more AI suggestions.
Real engineering work that needs to get shipped.

So we launched Ovren as an AI engineering execution product for real backlog tasks:
AI frontend and backend engineers that work inside your real codebase, execute scoped work, and return reviewable code updates.

We've had people tell us Clarity changed how they train, how they work, and how they sleep.

Most interestingly, people have told us that they are in fact drinking more caffeine, safe in the fact that they understand how the dose is being processed in their body and how it could be impacting their sleep if not timed correctly.

This isn't we invented anything. Because we put the science somewhere people actually use it - on their phone, in their routine, before the decision gets made.

Sleep debt doesn't just make you tired. It degrades decision-making, reaction time, and emotional regulation, and you often can't feel how impaired you are.

Most people try to fix it with more caffeine. That makes it worse.

Clarity helps you use caffeine to perform better today without destroying tomorrow.

5 days until our Product Hunt re-launch. Follow along. We're excited to show you the changes since the last launch.

Hey everyone! Just shipped v0.10.17 here's what's new:

- Boards New /boards slash command with node types, collapsible groups, and node notes

- Terminal Drag-to-Split Drag to split and unsplit terminal tabs

- Dark Mode & Themes Refined surface system and improved colors

Hey Kalendar fam

We just launched our newest product Onform on Product Hunt today and would love your support!

Onform is an alternative to Typeform and Jotform. Build and manage forms completely through Claude Desktop using plain language no dashboard required. Intake forms, post-meeting surveys, feedback forms all of it, just by chatting.

Basic plan allows you create as many forms, and get many responses as you want.

I like Lambda for a lot of things, but there s a very specific point where it stops feeling elegant.

Usually it starts with something like:

• a job that runs too long

• a workflow that should keep going in the background

• a task that needs better isolation or custom runtime behavior

• a system that starts needing cron, retries, webhooks, logs, and routing in one place

And then the answer often becomes: move to Fargate, ECS, Step Functions, EC2, or stitch multiple services together.

I ve been using a lot of AI-generated code lately, and while it definitely speeds things up, security feels like a weak spot.

I ve run into issues like missing auth, exposed endpoints, and weak configs stuff that AI doesn t really flag unless you explicitly ask.

Curious how others are handling this:

• Do you rely more on manual reviews or tools?

• Any workflows that consistently catch vulnerabilities?

• Have you faced any real incidents because of AI-generated code?

Hey everyone - quick update on DeployHermes (managed hosting for Hermes agents on Fly.io).

Since our last public release (right after we moved the stack to Vercel), we ve been heads-down on reliability and on features people actually asked for. Here s what s new:

For months, our most requested feature at Murror was a chat function. Users wanted to talk to the AI the way they talk to a friend. It seemed obvious. Every competitor had it. Every feedback form mentioned it.

So we built it.

We reworked our pricing to make it simpler and give more value on every plan.

What changed:

Pro and above all get more credits at the same price. Starter drops to $20 to make it easier to try.