Credentials. The app reads quotas from each vendor with the agent's existing sign-in or configured key, so only run it on a Mac you trust and check which accounts you enable in Settings.
Who it is forA developer running Claude Code, Codex and other agents at once who keeps losing track of how much quota is left.
The problemQuota limits are spread across several agent tools, and checking each one interrupts the work in the editor or terminal.
The outcomeA glow at the notch or on a screen edge that turns green, yellow or red as each quota fills, with the numbers one hover away.
What you need first
- A Mac running macOS 14 or later
- Xcode or the Xcode Command Line Tools with a Swift 6 toolchain
- Git, to clone the repository
- At least one supported agent installed and signed in, such as Claude Code or Codex
Steps
- Run
git clone https://github.com/jazzenchen/agent-hud-open.gitand thencd agent-hud-open. - Run
make checkandmake testto check the source and run the unit tests. - Run
make runto build and open build/Agent HUD Open.app, signed ad-hoc for local use. - Hover over the glow to read each quota's share used and reset countdown.
- Open Settings to choose the accounts and quotas to show, and set each display's mode to Simple or Dynamic if you want one logo per agent.
Prompt for your agent
In the agent-hud-open repository, run `make check`, `make test` and `make run`, then report whether build/Agent HUD Open.app opened. Verify that at least one agent quota shows a colour glow, and state which quota it is.
Caveat. Agent HUD finds installed agents by itself, but the quota readings depend on each vendor's data, and some agents such as Hermes Agent report no quota at all.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page