AI account assistant · macOS

Manage multiple Claude & Codex accounts.

Your AI accounts. Taken care of.

Tokenalytics is an AI account assistant in development for macOS. It brings multiple AI accounts, provider-reported usage limits, and reset times into one place, so account administration takes less of your attention.

Built for people moving between authorized personal and work accounts in Claude Code and OpenAI Codex. Public downloads are not available yet.

Beyond a usage counter

A percentage answers how much you have used. Account management adds the context: which account you are looking at, which usage window applies, and when the provider says it resets.

Keep account identities together
Review accounts by provider instead of keeping a separate mental list of personal and work logins.
Check allowance and reset time
Inspect each account's reported quota windows and reset information. A reset time is not a billing renewal date, and missing data is not proof that an account is ready.
Stay in control
Account selection is user-directed by default in the current development build. Automatic failover is opt-in; availability depends on the integration. Uninterrupted active sessions are not promised.

What the current build covers

Development scope, reviewed September 6, 2026. This is not a released-feature guarantee; final compatibility will be confirmed with the public release.

Claude accounts: Account details and provider-reported usage windows for the Claude coding workflow. This is not Claude conversation analytics.
OpenAI Codex accounts: Account details, quota windows, and reset information for Codex. Ordinary ChatGPT conversation limits and API invoices are separate.
Token expiry: Expiry information where the integration exposes it. Token expiry does not establish when a paid subscription renews.
Platform and availability: macOS is the focus of this introduction. Tokenalytics has not launched; no public download or release compatibility is promised here.

Common questions

Is this an AI chatbot?

No. “Assistant” describes help with account administration, not a general-purpose chatbot or a claim that an LLM makes account decisions.

Does it track ChatGPT usage or API costs?

The focus here is Claude and Codex account allowance. Codex access through a ChatGPT plan should not be confused with ChatGPT chat limits or separately billed API consumption.

Does account management increase my limits?

No. Provider limits still apply. Only connect accounts you are authorized to use and follow your provider and organization's policies.

Will it cancel subscriptions or warn before every limit?

Billing management, universal advance alerts, and exhaustion forecasts are not promised. Current scope is account status and usage visibility, with provider-dependent information.

Where can I check provider rules?

Consult Claude's usage-limit documentation and OpenAI's Codex plan documentation. Provider policies and available fields can change.