I asked Fable to dig into the logs and do a deep research for relevant evidence:

Related reports counted hundreds of Gatekeeper denials for Codex’s own main executable, eventually exhausting syspolicyd file descriptors and causing unrelated notarized apps to be reported as “damaged”:

https://github.com/openai/codex/issues/25882 https://github.com/openai/codex/issues/28071

Quitting Codex and restarting syspolicyd is only a temporary recovery. The useful upstream action is to identify the launch/update/watchdog caller, add exponential backoff plus a hard retry cap, and publish the first known-fixed desktop build.

I use Claude Code, Codex and OpenCode together, but I wanted a desktop workflow that wasn’t tied to one of them. I kept coming back to my terminal and keep forgetting which agent had finished what. Especially, I want to manage different cron jobs together (Claude Code is better at frontend so I want it to write SEO pages, while Codex is better at logic so I want it to review PRs).

So I built Cetus, with support for different runtimes, and many other stuff(quick launcher allowing you to use it using a global shortcut, cron jobs for different runtime, and kanban view). Under the hood it's a Tauri app with a Rust host.

I’d especially like to know: Do you also switch between multiple agent runtimes, or have you mostly settled on one? Does Cetus make sense to you?

Comments URL: https://news.ycombinator.com/item?id=49084323

Points: 2

# Comments: 1

I've been experimenting a lot with Nano Banana AI recently, and noticed many users (myself included) often get stuck figuring out how to write effective prompts or discovering new ways to use the model.

To help with this, I built a new site: https://nanobananaprompt.io, which organizes a collection of prompt templates specifically for Nano Banana AI.

The site features categorized templates for design, e-commerce, image editing, anime/games, and creative projects—examples include 16-bit game style, AI figure generator, sticker creation, and background replacement. Each template includes a ready-to-use prompt, which you can copy with one click.

I'm continuously updating the site and working on a feature to allow users to submit their own prompts. If you're a heavy Nano Banana AI user or just getting started, feel free to check it out. Feedback and suggestions are welcome!

Hope this helps save some trial-and-error time and sparks new ideas for your projects.

Comments URL: https://news.ycombinator.com/item?id=45129145

Points: 2

# Comments: 0

I wanted to share something I’ve been working on: Mailpod (https://mailpod.io/), an app that automatically summarizes your daily emails and turns them into a podcast you can listen to.

The idea is simple: instead of spending an hour sifting through your inbox at your desk, Mailpod lets you “hear” your emails while commuting, working out, or just on the go. It’s designed for anyone who wants to reclaim their time and stay on top of their inbox without being glued to a screen.

If you’re interested, you can check it out on the App Store: https://apps.apple.com/app/mailpod-your-email-to-podcast/id6...

Would love to hear your feedback or thoughts!

Comments URL: https://news.ycombinator.com/item?id=44787034

Points: 3

# Comments: 0

I find myself have nothing to do but scroll on social media endlessly when waiting for AI thinking, especially when "Agentic" AI becomes today's trend and thinking time is getting longer and longer.

So I made this, part of it is inspired by the Thronglets in Black Mirror. The art asset is credited to my wife. Hope you guys enjoy it :)

Comments URL: https://news.ycombinator.com/item?id=44007244

Points: 4

# Comments: 5

I’ve developed a web app that lets you turn static Ghibli-style images into animated videos. It uses AI to create smooth, dynamic animations from your uploads. I will also add Ghibli-style images generation abilities in the app soon. I’d love to hear your feedback and see what you create with it :)

Check it out at https://image2video.app/.

Comments URL: https://news.ycombinator.com/item?id=43718352

Points: 4

# Comments: 12

I want to focus solely on Bluesky, which is the competitive advantage since most of the schedulers do cross-platform posting, and cannot focus too much on a single platform.

Two months ago, I joined Bluesky and built an app called Skyblaze.app. It’s a tool designed to help users write better content, schedule posts, and engage more effectively with the community. I created it because I personally wanted something like this, and I’ve enjoyed using it myself.

After launching the app across various platforms and communities, I didn’t manage to attract any paying customers. This has left me at a crossroads:

Should I double down on this project—adding more features, improving the marketing (SEO, outreach, etc.), and finding my audience? Or is it time to cut my losses and move on to another idea?

I’d love to hear from other indie hackers: • How do you evaluate whether to persevere with a project or pivot away? • Are there specific metrics, signs, or gut feelings you rely on to make that call? • Have you faced similar situations, and if so, what did you learn?

Any advice, frameworks, or personal anecdotes would be incredibly helpful. Thanks for your thoughts!

Comments URL: https://news.ycombinator.com/item?id=42831760

Points: 1

# Comments: 2

Curious about your next steps—are you taking a break, or planning to build another startup?

I was so scared that I cannot move but trembling on my chair. Luckily my mom was near and she heard my scream and turned off the computer.

I actually find connecting with my real-life friends a meaningful and satisfying experience.

But things are getting worse once I started to follow influencers and those I don't know in my real life.