Show HN: Tokenmaxx – CLI that merges usage across Claude Code and Codex accounts Rubric Labs released Tokenmaxx, a CLI tool that merges usage across multiple Claude Code and Codex accounts into a single dashboard with auto-rotation between accounts based on rate-limit pressure. The tool runs a loopback proxy on 127.0.0.1:8459, stores credentials in the macOS Keychain, and defaults to switching at 90% threshold to avoid hitting hard limits. One dashboard for all of your Codex and Claude Code accounts. Easily switch between them, and monitor usage. macOS · Bun · a Rubric Labs project · not affiliated with OpenAI or Anthropic bun add -g tokenmaxx tokenmaxx starts the dashboard You run a fleet of coding agents using multiple Codex or Claude accounts: tokenmaxx keeps them all signed in locally and lets you choose which one your clients use. A small proxy on your machine attaches the active account's credential to each request, so a switch takes effect on the very next request, even mid-turn. Your credentials live in the macOS Keychain and never go anywhere except to the provider that issued them. Run tokenmaxx . Accounts shows every account and its live rate-limit windows, colored by pressure, with plan tier and reset countdowns inline. Rows sort by pressure; the ● marks where traffic is going right now. Analytics is combined token throughput across all accounts and both providers, with the ≈ cost of that usage at API list rates. Tokens are metered as responses stream by, never buffered, so every number is cross-checkable against your clients' own session logs. Press m for the full pricing breakdown per model. Settings holds the master on/off per provider, then auto-rotation, the switch threshold, and cooldown, applied live. Turn it on and tokenmaxx watches the active account's rate-limit windows. When the fullest one crosses your threshold, it switches to whichever of your accounts has the most room. The default threshold is 90%, which leaves the last stretch of every window alone in case you want it later. If an account hits a hard limit in the middle of a request, the proxy retries that request on your next account with room. tokenmaxx auto both on --threshold 90 or: codex | claude … off A single loopback proxy on 127.0.0.1:8459 , and the clients you already use. Account per request. The proxy reads which account is active for each request and attaches its credential. Switching lands on the next request. Pressure read for free. Both providers report rate-limit state on every response; the proxy reads it as traffic streams by, so it always knows how full the active account is, with zero extra requests. Official apps only. Your subscription login is for Claude Code and Codex. If you're building something custom, use an API key from the provider. tokenmaxx doesn't turn a subscription into an API plan. tokenmaxx live dashboard tokenmaxx login