Codex Usage Menubar

Tiny macOS menu bar that shows how much Codex you have burned without digging through menus.

by @gameofbitcoinAdded Aug 23, 2026

got tired of clicking through menus just to see how much Codex I’ve burned through So I built a tiny macOS menu bar app to keep the usage in check github.com/gameofbitcoins… Tibo @thsottiaux - maybe Codex should just ship this by default?

11:51 AM · Aug 21, 2026

Read 3 replies

Visit project View post on X

Related builds

Mac Developer Bridge

MCP bridge so ChatGPT can operate your real Mac: shell, files, PTYs, background jobs and read-only Codex history. MIT. No model calls.

Alex

@abenz95

·Follow

I wanted ChatGPT to operate the Mac where my work lives. So I open-sourced Mac Developer Bridge: shell, files, real PTYs, background jobs + read-only Codex history. MIT. No model calls. Very much not sandboxed. github.com/alexanderradah…

4:25 PM · Aug 15, 2026

Halo

Post-training framework for open-source models. Up to 2.8x TRL throughput, less peak memory, weights stay HuggingFace-native.

White Circle

@whitecircle

·Follow

Introducing Halo, the best framework for post-training of open-source models. Halo delivers up to 2.8x the throughput of stock TRL with less peak memory, while models stay in their native HuggingFace format. Star us on GitHub: github.com/whitecircle/ha…

Watch on X

5:28 PM · Sep 21, 2026

1.9K

Read 165 replies

open source ai developer tools

Visit project

Sep 22, 2026

MetalML

scikit-learn workflows on Apple Metal GPU. Change the import, keep fit/predict. Falls back to CPU when it has to.

Tudor Iustin

@tudoriustin22

·Follow

I just open-sourced MetalML. MetalML is a open-source library that brings up to a 15x speedup on native Apple Metal GPU acceleration to scikit-learn style machine learning workflows in Data Science. MetalML dispatches eligible work through native Metal kernels + Metal Show more