davidcann

You can block file access on macOS by running codex in a sandbox with my app: https://multitui.com

It works for me, but only if I hold the phone up in front of my face, basically perpendicular to the road.

Thanks for the report. I messed up the CDN settings. It looks fixed now.

I built this with 94% written by coding agents: https://buildermark.dev/

The complete log of all prompts and commits is here: https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

Photoshop alternatives already exist and are cheap or free, like Affinity.

Why create a Final Cut Pro alternative when it’s so cheap from Apple?

Many existing apps can be mostly cloned by a small team over 6 months or a year, but the challenge is finding customers willing to switch. You still need to add something new and useful, then reach customers somehow.

You can also sandbox TUIs, with full control of the sandbox parameters. To do this on macOS, you can use: https://multitui.com

Buildermark calculates how much of your code is written by agents. Open source, local, and cross-platform (written in Go).

https://buildermark.dev

> 70% of committed code originating from AI.

How are they calculating that? They could be using my tool, Buildermark, but I do t think they are: https://buildermark.dev

Thanks for the feedback. I agree that it’s changing very fast, which is why my thesis is that this tooling will be needed to help everyone on the team keep up.

Is your team measuring how much of your code is being written with claude and comparing amongst the team, like what works best in your codebase? How are you learning from each other?

I’m making a team version of my buildermark.dev open source project and trying to learn about how teams would like to use it.

To help you decide if you should keep your Claude subscription, you can see how much of your code is written by Claude Code with my project (open source, local): https://github.com/gelatinousdevelopment/buildermark

I’m working on Buildermark (open source, local) that calculates how much of your code is written with coding agents.

It scans your claude and codex history to find edits and matches those to git commits (even if the code was auto-formatted).

https://buildermark.dev/

You can browse all 364 prompts that wrote 94% of the code here:

https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

Native macOS sandbox terminal:

- UI for sandbox-exec to protect filesystem - Network sandbox per domain - Secrets filter via gitleaks - Vertical tabs option

It's highly customizable. You generate native macOS app wrappers for each terminal app, each with its own rules and customizations.

https://multitui.com

I made a native macOS app with a GUI for sandbox-exec, plus a network sandbox with per-domain filtering and secrets detection: https://multitui.com/

No, I run a separate URL detection to make links clickable. However, SwiftTerm just added link detection a few days ago and I haven’t had time to look into theirs yet.

My app is a macOS terminal wrapper with nice GUI for sandbox-exec and network sandbox. I just added a vertical tabs option too. https://multitui.com

Yeah, that’s understandable. Many open source macOS-only apps seem to get abandoned, so I’m trying to build something sustainable.

It uses only 3 dependencies that are very well known and widely used, so supply chain risk is minimal. That leaves me, the developer, as the main point of trust.

SwiftTerm, for not. I may switch to ghostty when their library is ready for embedding.

Yeah, they all do sometimes, but the agent decides what to allow and they can choose to not use it. This gives the user full control of the sandbox and you can run the agent in yolo mode.

I made a UI for this to run terminal apps, like claude and codex: https://multitui.com

The same concept is possible on Linux, but I don't think anyone has created a nice UI for it yet. There was a post yesterday about doing it on the command line in linux: https://news.ycombinator.com/item?id=46874139

One of the nice things in Multitui is that it monitors what is blocked and gives you a way to add a read/write rule from the UI.

I’m seeing log delays too the past couple of days… something like 14 hours, in my case.

My app does this on macOS! https://multitui.com

Thanks! For network sandboxing, I was thinking something like what Little Snitch can do, but more customized... maybe block POST requests and long GET request strings or anything that looks like too much code or secrets.

Shameless plug, but you can sandbox codex cli without a container using my macOS app: https://multitui.com