English | 中文 | 日本語 | 한국어 | Español | Português
Local token & cost dashboard for AI coding tools
Try it without installing → tokdash.github.io/demo
Table of Contents
- Quick start
- One package, four views
- Install & run
- Features
- Quota tracking (optional)
- Cost accuracy note
- History retention
- Roadmap
- Contributing / security
- Documentation
- License
Quick start
pipx install tokdash
tokdash setup
That's it. tokdash setup detects the runtime, installs a managed one if
needed, registers a local service, and prints the dashboard URL —
http://127.0.0.1:55423. Full options, first-run notes, and updates live in
Install & run; prefer to look around first? The
live demo runs on the real UI.
One package, four views
One local package, one local data index — and four ways to read it. Every surface parses the same session logs on your own machine, so the browser dashboard, the terminal, the menu bar, and your agent's statusline always agree.
| View | What it is | Reach for it when |
|---|---|---|
| WebUI | The full dashboard: Overview, Sessions, Stats, Report, Quota, Servers | You want the whole picture, charts, and drill-down |
| TUI | tokdash tui — Overview, Report and Quota in the terminal |
You live in the terminal and want the numbers without a browser |
| Companion | Native menu-bar (macOS) / notification-area (Windows) app | You want today's spend and quota visible all day, dashboard closed |
| Statusline | A live token/cost item inside your agent's statusline | You want the cost ticker exactly where you type |
WebUI
The dashboard is a single page served by the local FastAPI app: exact input / cache / output token breakdowns, per-tool and per-model tables, a contribution heatmap, a week/month/year Report, per-provider Quota windows with reset countdowns, and a Servers tab that combines and compares several machines. Click any screenshot to open the live demo.
Overview
|
Usage Report
|
Quota tracking
|
Multiple servers, one total
|
Light and dark follow your OS appearance. The app ships 17 style themes, light/dark modes, PWA install, and six UI languages (English / 中文 / 日本語 / 한국어 / Español / Português).
Terminal dashboard (TUI)
Prefer to stay in the terminal? tokdash tui opens the Overview, Report,
and Quota tabs without a browser, reading the same local index (and the
shared on-disk database when a tokdash serve is running beside it).
TUI — Overview
|
TUI — Quota
|
tokdash tui
Keyboard
| Key | Action |
|---|---|
q |
Quit |
r |
Refresh the current tab |
1 / 2 / 3 |
Switch to Overview / Report / Quota |
t w m y a |
Jump to a period directly (both period tabs; t/a are Overview-only) |
p |
Next time window (forward-only cycle) |
[ / ] |
Step one whole calendar period back / forward — never into the future |
0 |
Back to today |
u |
Poll quota (Quota tab only) |
? |
Help overlay with all keys |
One-shot report CLI
For a one-shot report you can pipe or script:
tokdash report --period week
The period is a flag, not a positional argument. Accepted values: today (the
default), week, month, year, all, a number of days, or Nd/Nw/Nm/Ny
shorthand; week, month and year are the same calendar-aligned windows the
web Report tab shows. tokdash report also accepts --json, --pretty and
--output <file>, following the same conventions as tokdash export.
Companion status bar app
An optional native menu-bar app for macOS and notification-area app for Windows: a compact, read-only view of the Tokdash service without the dashboard open.
|
|
| macOS menu bar | Windows notification area |
Windows — Microsoft Store (recommended, signed by Microsoft, requires Windows 11):
Direct download — the latest companion release:
a universal DMG (arm64 + x86_64, macOS 14+) and a self-contained portable ZIP
(x64, Windows 11; Windows on Arm via x64 emulation).
What it shows, and how setup works
- Today's cost, tokens, messages, and month-to-date usage
- Combined totals and server-grouped quota from multiple Tokdash endpoints
- Codex, Claude, Kimi, MiniMax, Antigravity, Grok, and Z.ai quota windows
- Relative reset times and optional low-quota notifications
- System language detection plus English, Simplified Chinese, Japanese, Korean, Spanish, and Portuguese
- No telemetry, credential discovery, port scanning, or direct log parsing
Setup: run Tokdash 1.5.2 or newer (Install & run), install the
companion, and it connects to http://127.0.0.1:55423 by default — its settings
let you add, test, name, or remove explicit endpoints, including private Tailscale
Serve URLs. The companion only contacts the endpoints you configure; low-quota
notifications and launch at login are opt-in.
Checksum, update, and removal instructions live in the companion release guide.
Statusline
The local API can power a statusline item in your coding agent showing live token/cost stats:
Ready-made templates (bash and PowerShell), install/config, and the endpoint
reference live in docs/guides/statusline/.
Install & run
Platform support
- Linux (including WSL2): supported
- macOS: supported
- Windows (native): experimental
Prerequisites: Python 3.10+ and one or more supported clients.
Install
Recommended isolated install:
pipx install tokdash
If you do not use pipx:
python3 -m pip install --user tokdash
First run
Run the onboarding wizard:
tokdash setup
The wizard configures a reversible user-level background service when the platform supports
one, then prints the dashboard URL (default: http://127.0.0.1:55423). If no supported
service manager is available, it records setup state and prints foreground run guidance. It
uses localhost-first defaults, does not require sudo for the local service, and keeps your
usage history unless you later uninstall with --purge.
For a non-interactive setup from an agent, script, or bundle, run
tokdash setup --auto --json; to preview what setup would change, tokdash setup --dry-run.
To expose the dashboard explicitly on all network interfaces with writes disabled, run
tokdash setup --bind 0.0.0.0; review the remote-access guide first.
Then check the install:
tokdash doctor
doctor checks the runtime, background service, configured port, data paths, and update-check
status. Use tokdash doctor --json for automation.
Update or remove
tokdash update # upgrade the managed runtime and restart the service when possible
tokdash uninstall # reverse exactly what setup created; keeps usage history by default
update only drives install methods Tokdash can safely manage. If your runtime was installed
by a package manager Tokdash does not own, it prints the exact manual guidance instead of
mutating that environment.
Existing installs: migration from before v1.0
If you installed Tokdash before the onboarding flow, upgrade first:
pipx upgrade tokdash
# or: python3 -m pip install --user -U tokdash
Then run tokdash doctor and tokdash setup when you want Tokdash to manage the background
service. If you already have a hand-written systemd or launchd service, setup does not
silently replace it: it refuses unmarked tokdash.service / plist files by default. Keep
managing that service yourself, remove it before setup, or run tokdash setup --force after
checking tokdash setup --dry-run. --force also handles pre-1.0 services that already
occupy port 55423 but do not expose the new /health fingerprint: it rewrites and restarts
the existing tokdash.service. Use tokdash setup --no-service to skip service creation.
If your current setup uses a conda/system/user-pip interpreter and you want tokdash update
to manage future upgrades, migrate the service to Tokdash's setup-owned venv:
# Upgrade the tokdash command you are about to run, for example:
python3 -m pip install --user -U tokdash
# or, for a conda base install:
conda run -n base python -m pip install -U tokdash
tokdash setup --runtime venv --force
tokdash doctor
This keeps your usage history under ~/.tokdash, rewrites the user service to run
~/.tokdash/runtime/python-venv/bin/python -m tokdash, and lets future tokdash update
upgrade that managed venv and restart the service. If you installed with pipx, you can
instead keep the pipx runtime and upgrade with tokdash update or pipx upgrade tokdash.
Foreground fallback
If you only want a one-off foreground process:
tokdash serve
Open http://127.0.0.1:55423. Use tokdash serve --port <port> if the default port is busy.
By default tokdash serve opens the dashboard in your browser once on startup; pass
--no-open to disable it. A bare tokdash with no command just prints the command help
and exits — it no longer starts tokdash serve behind your back.
For full onboarding details — runtime choices, WSL/systemd behavior, macOS launchd,
Tailscale, bundling, update checks, and safe uninstall semantics — see
docs/guides/ONBOARDING.md. For remote access through
Tailscale Serve, SSH forwarding, or an explicit network bind, see
docs/guides/REMOTE_ACCESS.md.
Features
- Exact token counts: Input/Output/Cache token breakdowns
- Session explorer: per-session drill-down
- Contribution calendar: 2D heatmap + 3D isometric view with Tokens/Cost/Messages metrics
- Report tab: a week / month / year-to-date report of your own agent activity, with a shareable card for each tier of detail. Every export writes a light and a dark PNG
- Quota tab: subscription window bars with reset countdowns for nine providers. Codex windows work out of the box from local logs; most other sources need opt-in live polling
- Terminal dashboard [new]:
tokdash tui— Overview, Report and Quota in the terminal, no browser required - Companion status bar app: spend and subscription quota from the macOS menu bar or Windows notification area — on the Microsoft Store for Windows
- Statusline integration: a live token-usage indicator inside Claude Code's statusline (or any agent that can hit a local HTTP endpoint)
- Multi-server views: add WSL, macOS, and other Tokdash servers in Settings; combine usage across any selection while keeping quota grouped by machine. See remote access.
- Themes and app polish: 17 style themes, light/dark mode, PWA install support, UI in six languages
Supported clients
Tokdash reads the local session logs of 27 supported agents — the pill row above names them; the full matrix (usage & cost / Session Explorer coverage, per-client data paths, overrides, and source-specific accounting notes) is in Supported clients.
Quota tracking (optional)
The Quota tab shows subscription utilization windows and reset countdowns for nine providers. Codex's 5-hour/weekly windows work out of the box from local logs (treat them as an estimate); accurate Codex consumption and every other provider — Claude Code, Antigravity, MiniMax, Kimi Code, Grok, Z.ai, OpenCode Go, Command Code — come from opt-in live polling: Tokdash calls each provider's own quota endpoint with the sign-in your CLI already has. Off by default, per-provider consent, results kept in the local database.
The consent commands, master switch, poll cadence, and per-provider credential
notes are in docs/reference/QUOTA.md.
Cost Accuracy Note
Token counts depend on what each client logs locally. Costs are computed from the bundled pricing database (src/tokdash/pricing_db.json) by default, or from your saved dashboard pricing override at <data_dir>/pricing_db.json when present. Either way they may lag real provider pricing — use as an estimate and verify against your billing source if it matters.
History retention
Tokdash reads each client's local session logs; the local SQLite index cannot recover logs deleted before they were indexed. Only two supported clients delete old sessions by default, and both are a one-line fix:
- Claude Code: add
{ "cleanupPeriodDays": 3650 }to~/.claude/settings.json(and any alternateCLAUDE_CONFIG_DIR). - Gemini CLI: set
{ "general": { "sessionRetention": { "enabled": false } } }in~/.gemini/settings.json(workspace settings override user settings).
Every other supported client keeps history indefinitely by default. For the full per-client survey, fix details, and what the local SQLite index does and does not preserve, see docs/reference/HISTORY_RETENTION.md.
Roadmap
See docs/development/ROADMAP.md.
Contributing / security
- Contributing guide:
docs/CONTRIBUTING.md - Security policy:
docs/SECURITY.md
Documentation
Full documentation lives in docs/ (start at the index), grouped into:
- guides/ — task-oriented setup: onboarding, remote access, statusline, background service.
- reference/ — lookup material: API reference, configuration, quota internals, supported clients, history retention.
- development/ — changelog, releasing, roadmap, and public
technical-notes/.
License
MIT License - see LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for tokdash 2.6.18
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| tokdash-2.6.18.tar.gz | 2.8 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tokdash-2.6.18-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 4.7 MB
Release files / tokdash-2.6.18.tar.gz
| Download URL | tokdash-2.6.18.tar.gz |
|---|---|
| Size | 2.8 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
80a76e7a90058cb5768aa1d99aec587133fe6a833af610ccd398f56cfb0aa263
|
|
BLAKE2b-256 checksum How to use checksums |
9e8eb7dc9dcbc4ca6529e097800c64155179f0cc990cad84c82f259b39556910
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 16, 2026.
Transparency logRelease files / tokdash-2.6.18-py3-none-any.whl
| Download URL | tokdash-2.6.18-py3-none-any.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3a711fbc62ee7a5eb1f8a9d5aa0b291b6f6fa5381c16570d3d193aae8e3f91c2
|
|
BLAKE2b-256 checksum How to use checksums |
b4e4bae7d73d0da7274360948e911201978de11d65cf5a589617923503f8e661
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 16, 2026.
Transparency log
