Agent Runway

For Claude and OpenAI subscribers

Know your runway

Agent Runway lives in your Mac's menu bar and shows how much of your weekly AI allowance is left — paced against how long until it renews. One glance tells you whether to push hard or ease off.

Version 2.18.1

Free, or Pro for $2.99 once · macOS 15 or later · Apple Silicon & Intel · Notarized by Apple

The Runway panel: Claude 82% left, renews in 20 hours, blue, and on course to last to renewal; OpenAI 59% left, renews in 4 days, green, with a dotted projection running out on Friday and a reset credit expiring in 3 days

Pacing, not prediction

Five cells. Four colors.
One glance.

Runway compares the allowance you have left with the time left in your weekly window. Burn faster than the clock and the cells warm up; bank a surplus and they cool to blue.

  • Blue — plenty available. At least twice the allowance the clock says you need, and 20% or more left.
  • Green — roughly on pace for the week.
  • Yellow — getting tight. Ease off to make it to renewal.
  • Red — very tight. You'll likely run short.

⏳ appears when you're blue and renewal is under 48 hours away: a nudge to use the surplus before it resets.

Try it

86% left
24h

What's inside

Everything the week needs, nothing it doesn't

Glide path

Your allowance across the week against the even-pace diagonal, with each day named and today lit. Above the line, you're ahead. Pro scrolls it back through past weeks.

Reset warnings

Surplus about to reset gets an hourglass. Reset credits are called out a week before they lapse, and hovering the resets line lists them all, soonest first — Runway never spends one. An early reset gets a line on the card.

Token activity

24 hours of bars for this Mac, split into cached history, new input and output. Pro adds 7 and 30 days.

Every limit that can stop you

The week, the 5-hour session, and a model's own weekly cap, like Fable's: shown when it's tighter than the week, with a banner once it's used up.

Share your burn

Drag across the chart for any span, then copy a share image or Wordle-style text, logo and all.

Fault tolerant

Offline, signed out, CLI missing, enterprise plan — it says exactly that, keeps the last good reading, and retries. When Codex has no allowance to show, OpenAI’s card says so in one calm line, with help a click away.

Notifications Pro

Told once, when it matters

Runway stays out of the way until something changes what you'd do next: you're back in, your week reset early, you're heading for empty, or you're about to leave a lot on the table.

Each one comes once for each thing that happens and never repeats what another has just said. Every one has its own switch in Settings → Tune interruptions.

The examples are the app's own words, for the same Tuesday morning as the panel at the top.

  1. You're back Once, when a session limit or an outage that stopped you ends.

  2. Early reset or new credit As soon as your week resets early or a reset credit arrives.

  3. Running out When your pace would run out at least 12 hours before renewal. Once a week at most.

  4. Plenty to spare When ⏳ shows and 30% or more would go unused. Once a week at most, in the daytime.

  5. Morning report Each provider in a line at 6 AM.

Activity

Where the tokens actually go

Most of what an agent "uses" is its own history, re-read from the prompt cache on every turn. The Activity tab draws that as frosted glass, with the new input and output rising inside it — then flips to New only to show what you really added. On smaller displays, the cards scroll while the header, range controls and footer stay in reach.

Pro adds a list under each chart, By project to start: the same tokens by repo, following whatever you select, with worktrees folded into the repo they came from. Click its title to switch to By agent, main sessions against subagents, or By model, split by model and effort. Claude's card splits the week too, between Claude Code, chats and Cowork.

Want room to look closer? Click Details on a Runway or Activity card for Activity details: your allowance and your tokens on one chart, beside the complete breakdown.

Read from the session logs Claude Code and Codex already keep on your Mac; after the first scan, Runway reads only appended data. Copy Image in the Activity window explicitly includes the visible private breakdown and historical chart, with Runway branding and dates. Check what's visible before sharing. Copy Card, Copy Snapshot, the other image and text shares, CLI and MCP still exclude private breakdowns and past-week curves.

Activity tab with a four-hour span selected: the readout shows all tokens, cached, new input and output for exactly that span
Drag to select · 4 hours
Activity tab in light mode, new tokens only over 7 days: input bars with a darker output base, and a By project list under each chart (its title opens a menu for By agent and By model), with harbor-api leading Claude's last 7 days and tidepool-web leading Codex's
New only · 7 days · by project

Monitor

Your Monitor takes flight

Open Monitor from a card in the menu-bar panel. Keep a separate window for each Claude account, with its own view and size. In Current Burn, your last 20 minutes of activity choose the aircraft, while the selected period controls the totals. Pick Activity or Allowance when you want another view.

See what’s driving the work in your project or model mix. When your plan includes breakdowns, expand a project into its models or a model into its projects. Keep it small as a widget, or make it taller for the chart and detail.

Curious what those tokens would look like at API rates? Pro adds an estimated API-equivalent cost, including cached tokens. It’s a comparison, not your subscription bill or your allowance. Some models may not have a known price, and you can turn estimates off in Settings.

Start a one-time 14-day preview of the estimate when you choose, even if your original Pro trial has ended. The preview is for this feature alone.

A synthetic Claude Monitor: 3.4 million tokens, a $12 API-equivalent estimate and 82% weekly allowance left, with Harbor expanded to show its models, Sonnet 4.5 and Opus 4.6, and Atlas below
A compact Monitor beside your work

Activity details Pro

Your allowance and your tokens,
on one chart

Your allowance line runs over this Mac's token bars, each with its own axis and its own label, because they're different things: the line is your whole account, chats and other Macs included; the bars are only the session logs on this Mac. Rest the pointer anywhere and a small glass readout shows both at that moment, side by side.

Synthetic Activity details for Claude, last 24 hours and live: 1.38 million new tokens on this Mac, an $11.63 API estimate, and a blue 82% allowance line over gray token bars. The hover readout at 8:23 AM shows 82% left account-wide and 96K new tokens in the 8:20 AM bar. Projects are Harbor 50%, Atlas 33% and Orchard 17%.
Hover readout · 1 day · Claude

Drag to zoom. Drag across the chart and it zooms to exactly that stretch; the total and the Projects, Agents and Models lists always cover what you can see, nothing more. Esc (or Back) returns to where you were, and double-click steps out. Pinch (or ⌘-scroll) zooms where your fingers are, down to 20 minutes of recorded 10-minute bars, and a swipe slides earlier or later.

The whole story, in one strip. Under the chart, a slim strip holds everything Runway keeps, with a box around what you're looking at: drag it anywhere, or drag its edges. 20m, 1h, 3h, 6h, 1d, 7d and 30d are one click away.

Watch what's burning right now. Drag past the right edge and the view stays live from where you started: it reads Since 7:29 AM · live and widens with every refresh, totals and lists with it, so you can see which project is eating tokens while it happens. Live keeps Last 6 hours · live sliding along; turn it off to hold still and look around.

A view you can leave open. Your current allowance and the tokens in view sit side by side. When the provider reports it, a purple session marker at now shows its percentage; hover for the reset time. New window (⌘N) keeps another provider or range open beside it, and each window remembers its range, grouping, zoom and placement.

Try a sample on Free. The Details button opens a clearly marked Sample workspace with working ranges and breakdowns. It uses made-up data, separate from your own activity. Personal Details remains part of Pro and the trial. One quiet Details introduction helps eligible users discover it; Help → Feature tips provides deliberate replay and the automatic-tips preference.

Tokens aren't allowance: Runway never claims a share of your week from them. A dip in the line with no bars under it is real use, just somewhere other than this Mac. Copy Image copies the current viewport, including its visible breakdown and dates; nothing else shares it.

Synthetic Activity details in light mode after dragging to a live view since 7:29 AM: 1.06 million new tokens on this Mac, an $8.92 API estimate, and token bars under a blue 82% allowance line. The project list shows Harbor 50%, Atlas 33% and Orchard 17%.
Dragged past now · since 7:29 AM, live

Claude accounts

Every Claude account,
its own card

Use more than one Claude account on this Mac? Runway tells them apart by organization and gives each its own card, with its own activity: Claude A, Claude B and so on, until you rename them.

Live where you’re signed in. The account Claude Code is signed in to shows its allowance live, paced as always, on every tier; with two or more accounts a thin ring on its mark says it’s the one Claude Code is using. Any other keeps its card at its last reading, or, if Runway has never read it, says “Sign in to Claude Code for its allowance”. With Pro, every account stays live.

The Runway chart, on every card. This Mac’s tokens stand as bars behind each allowance line, on one scale across every card, OpenAI’s included, so a busy account looks busy beside a quiet one — on every tier. Open Monitor on a Claude card to keep that account in view. With Pro, Activity details can follow the Claude account too.

Last seen, not forgotten. Switch Claude Code to another account and the first one’s card keeps its week up to its last reading, shown as at most what was left then, and remembers when that allowance renews. It’s drawn in gray, never the pace colors, so a remembered number never passes for a live one.

Cowork counts. Sessions in Cowork, the Claude desktop app’s agent mode, now count toward your activity.

Account names stay on your Mac: shares say Claude, never which account.

The Runway panel with four cards on one token scale. Claude A, its mark ringed as the account Claude Code is using: 82% left, renews tomorrow at 6 AM, with the Runway chart's token bars under its allowance line. Claude B, not signed in: at most 31% left, last read Fri 8:00 AM, renews tomorrow at 6 AM, its gray line ending in a small ring at that reading and dashed on to now. Claude C: 'Sign in to Claude Code for its allowance' and 'Where's my allowance?', with token bars across the week. OpenAI: 59% left, renews Saturday at 1 PM.
Three Claude accounts and OpenAI · one token scale
Arrange your accounts in light mode, headed Accounts: a menu bar preview with marks for A, B and C and OpenAI, then one row per account. Claude A, Claude Code live, 82%; Claude B, marked Signed out, 31% in gray; Claude C, activity only; OpenAI, Codex live, 59%. Each Claude row shows a short organization ID and a small chart. Underneath, a 'Why one folder per account?' link and a note: Runway tells accounts apart by a one-way fingerprint of the organization, so two sign-ins to the same Team organization show as one account, and never uses, stores, shows or sends your email.
Settings → Arrange your accounts

Your accounts, your way. In Settings → Arrange your accounts, drag to reorder, click a name to rename it (emoji welcome), give each a short name for the menu bar, and choose whether and how it shows there.

Forget one you don’t need. Undo, or ⌘Z, brings it right back; later it waits under Recently forgotten with a Restore button. If a forgotten account turns up again within 30 days, it comes back as itself, name and place included.

Runway never uses, stores, shows or sends your email.

Several accounts Pro

Every account,
live.

A work Claude and a personal one, or two ChatGPT accounts? Runway reads each one’s allowance live, side by side, read-only, right on your Mac.

One folder per account. Sign each extra Claude account in once, in a folder of its own, or each ChatGPT account in a Codex home of its own. Runway reads it the way it reads your usual sign-in, and nothing comes out of any allowance.

Three steps, then it’s live. Settings → Arrange your accounts → ⋯ → Live reading… walks you through it: copy the command, sign in, and Runway notices by itself.

About once a month, sign in again. A Claude folder’s sign-in lasts about a month; its card and Settings row say the date it needs signing in again by. Codex renews its own sign-in while you use it.

Read-only, and it stays here. Runway never signs you in or out and never runs those commands for you. Your numbers never leave this Mac.

Live reading of more than one account per provider comes with Pro and the 14-day trial. Your usual Claude Code and Codex sign-ins stay live on every tier.

The Runway panel with four live cards on one token scale, each read minutes ago. Claude A, its mark ringed as the account Claude Code is using: 82% left, renews tomorrow at 6 AM. Claude B: 71% left, renews tomorrow at 1:41 AM. OpenAI A, its mark ringed as the account Codex is using: 59% left, renews Saturday at 1 PM, with a reset credit that expires in 3 days. OpenAI B: 55% left, renews Thursday at 9:41 AM. Each card has its own Runway chart.
Claude A and B, OpenAI A and B · each read live

Past weeks Pro

Is this week unusual, or is this just you?

One bar per finished week, oldest on the left, all on the same 0–100% scale: how much of the allowance you'd used by renewal. A triangle marks a week that ran out, a pause mark one where you hit the session limit, and a sparkle one the provider reset early. A dotted cap means “at least”: Runway's last reading came well before the week ended, so the real number can only be higher.

Codex's history arrives all at once, read from its logs. Claude keeps none, so Runway builds its row from its own readings, one week at a time from the day it starts watching. The morning report adds a line about the week that just finished.

Then go back and look. The end of last week peeks in at the left edge of the glide path, dimmed. Drag the chart, or swipe sideways on a trackpad, and each past week settles into place with a line saying how it ended, in the same words as the bars. Use the arrows below the chart to move between weeks too. The card shows up to eight finished windows; Runway saves up to 52 summaries per provider and 63 days of readings for the curves, so Claude's chart fills in as the weeks go by. Separately, it keeps a daily summary of this Mac's activity for good, on every tier.

A week Runway never saw shows as a gap, never an invented bar. History stays on your Mac unless you choose Copy Image in the Activity window to include the historical chart you're inspecting. Other shares leave it out.

The Past weeks card in light mode: eight bars for Claude, one of them with a warning triangle and two with pause marks, one with a dotted cap and a gap mark after it, and eight bars for Codex, with a plan change, three sparkle marks and one warning triangle. Under them, 'Used it all in 1 of the last 8 weeks' and 'Used it all in 1 of the last 6 weeks on Pro · 3 reset early'
Allowance used by renewal · Claude and Codex, 8 weeks each
Claude's card in light mode with its glide path viewing last week: the header reads 'Viewing last week', an orange allowance curve descends across day names We to Tu, with a dashed even-pace diagonal. Under the chart, 'Week to Sep 30 · 66% used'
Scrolled back to last week · Claude

Share your burn

Your last four hours, in one image.
Copy, paste, brag.

Terminal and AI agents

Your runway, where your agents can see it

Install the runway command from Settings, and your allowance shows up in Terminal, in your status line and in your AI agents. Now an agent can check there's room before it starts something big.

  • runway — the morning report's lines. --json gives scripts every number, and --refresh asks the app for fresh ones first.
  • runway statusline — one short line for Claude Code's status line, tmux or SketchyBar.
  • runway wait — waits out a session limit or an outage, then exits, so the next step in a script runs once there's room. --json says what's blocking and when it's back.
  • runway mcp — a read-only get_runway tool for Claude Code, Claude Desktop, Codex and Cursor.

Free; Pro adds the run-out forecast and longer token totals. It reads only what the running app already knows, never contacts Anthropic, OpenAI or anyone else, and sends nothing. man runway has the rest.

runway

🟦🟦🟦🟦⬛ Claude · 82% · 20h ⏳
↳ 🛬 At this pace it lasts to renewal
🟩🟩🟩⬛⬛ OpenAI/Codex · 59% · 4d
↳ ⚠️ 1 reset expires in 3d (3 total)
↳ 📉 At this pace you'll run out on Friday, about 21 hours before renewal

runway statusline

Claude 🟦🟦🟦🟦⬛ 82% · 20h ⏳  Codex 🟩🟩🟩⬛⬛ 59% · 4d

claude mcp add --scope user agent-runway -- ~/.local/bin/runway mcp

Claude

The same usage data behind Claude Code's /usage screen. When its sign-in needs refreshing, Runway runs claude -p /usage — a local command that costs zero tokens.

OpenAI

Runway asks the Codex CLI’s app-server for account limits. Codex setup helps find the local setup you use; recorded activity can remain available separately.

Activity

The CLIs' own session logs, and Cowork's, read in place on your Mac.

Read-only by design

It watches. It never spends.

  • Never sends a prompt or starts a session, unless you switch on the optional token read for an extra Claude account
  • Never uses a reset credit
  • Never refreshes or rewrites your sign-in — the CLIs do that themselves
  • Runs Claude Code with hooks off, so checks don't show up as sessions
  • No account and no analytics. Your numbers never leave your Mac

Free and Pro

Free shows where you are.
Pro looks ahead, and back.

14 days of Pro to start, then the free version keeps going for as long as you like. Pro is $2.99 once: no subscription.

Free

$0

  • The menu bar cells, ⏳ and the Runway card
  • A card for each Claude account, each with the Runway chart, and your usual Claude Code and Codex sign-ins live
  • The glide path: this week against even pace
  • The 5-hour session limit, and a model's own weekly cap, like Fable's
  • Outages on Claude Code and Codex
  • Reset credits, called out before they lapse and listed on hover, and early resets
  • 24 hours of token activity and a compact provider Monitor
  • Copy Card, Copy Snapshot, share images and text shares
  • The runway command, for Terminal, status bars and AI agents

Pro

$2.99 once

Everything in Free, plus:

  • Run-out forecast: when you'd run out at this pace, with a heads-up if it's early
  • Notifications when you're back, when your week resets early, and when there's plenty to spare
  • Quick allowance-drop alerts: opt-in rules for each provider, once per continuous drop
  • The 6 AM morning report
  • Where the week went: tokens by project, agent or model, and Claude's split by surface
  • Estimated API-equivalent token cost, including cache, where pricing is known
  • Activity details: your allowance and this Mac's tokens on one chart, drag to zoom from 63 days down to 20 minutes, a live view of what's burning now, and a complete, expandable breakdown, plus Copy Image of the visible details
  • Past weeks: up to eight finished windows at a glance, and the glide path scrolls back through recorded weeks
  • 7- and 30-day views of this Mac's activity (Runway records a daily summary on every tier)
  • Every account, live: more than one Claude or ChatGPT account read side by side, each in a folder or Codex home of its own

One key for all your Macs · Had Runway before 2.0? Pro is yours, free · Get Pro at the store →

Get started

Up and running in a minute

  1. 1
    Download

    Unzip AgentRunway.zip and drag Agent Runway to Applications.

  2. 2
    Connect your tools

    Claude Code on a Claude plan, and/or Codex (npm i -g @openai/codex). For ChatGPT subscription limits, use your ChatGPT sign-in. Codex setup can help find your local installation and read saved activity separately.

  3. 3
    Glance up

    A short guide checks your tools on first launch. After that Runway checks on its schedule and when you open it, and keeps itself up to date.

Version 2.18.1

Using Bartender or another menu bar manager? New items may start hidden — allow Agent Runway there.

Questions

Does checking use up my allowance?

No. Every check is a read. Claude's fallback, claude -p /usage, is a local command with no model call: zero tokens, zero cost. Codex is asked only for account and rate-limit data. Extra accounts in their own folder or Codex home are read the same way. The one exception is optional and off until you switch it on: an extra Claude account read with its own token sends Anthropic one tiny request per check, which uses a sliver of that allowance.

Why isn't it on the Mac App Store?

App Store apps must run in Apple's sandbox, which forbids exactly what Runway needs: running the claude and codex command-line tools and reading their session logs. Instead it's signed with a Developer ID and notarized by Apple, so it opens without warnings and never expires.

What leaves my Mac?

Your numbers never leave it: usage, readings and token history stay in ~/Library/Application Support/AgentRunway. Runway reads your allowance only from Anthropic and OpenAI, using their CLIs’ sign-ins, and checks their public status pages for outages (you can turn that off). A daily update check shows our server the app version and your IP address, like any download. A Pro key is checked on your Mac, offline. There are no analytics and no account, and we have your email only if you buy Pro. The runway command sends nothing either, but an AI agent you let run it passes what it reads to its model provider.

Will it nag me?

No. Each notification comes once for each thing that happens: one when you're back, one for an early reset or a new credit, at most one run-out warning and one heads-up about spare allowance a week, and the morning report. Quick allowance drop starts off; turn it on and set a rule for each provider to get one alert per continuous drop. Two never say the same thing. Each has its own switch in Settings → Tune interruptions, which also tells you if macOS has them turned off for Agent Runway.

Does a model's own limit change my colors?

No. The pace is always the whole week's. When a model like Fable has its own weekly cap and it's tighter than the week, the card shows it in a quiet line; once it's used up, a banner says when it's back and that other models still work.

Can my AI agents check it?

Yes. Install the runway command in Settings → Connect an AI agent, then give Claude Code a read-only get_runway tool with claude mcp add --scope user agent-runway -- ~/.local/bin/runway mcp (Settings has a Copy Command button). Claude Desktop, Codex and Cursor can run runway mcp too. It reads only what the running app already knows, so keep Agent Runway open. Whatever an agent reads goes to its model provider, like anything else you show it: Claude reading your Codex numbers sends them to Anthropic.

I'm on an enterprise or API-key plan.

There's no personal weekly allowance to pace, so Runway says so instead of guessing — and the Activity tab still shows your token burn.

Why is output such a small share?

Agents read far more than they write. Every turn re-sends the conversation so far, served from the prompt cache, so cached input dominates. Output is usually well under 1% of everything processed, and around a tenth of the new tokens.

Is the percentage exact?

The percentage comes straight from the provider and is authoritative. The cells round to the nearest fifth, with any allowance at all keeping one cell lit and all five reserved for exactly 100%.

Is this made by Anthropic or OpenAI?

No. Agent Runway is an independent utility and isn't affiliated with or endorsed by either company.