Moxie - Use any AI with Claude Code, switch accounts mid-task

Moxie is a Mac menu bar app for Claude Code. Use your ChatGPT plan, Gemini, DeepSeek, OpenRouter or local models in Ollama, all from the Claude Code you already use. Hit a usage limit? Pick another account in one click and keep the same session going. Every account's 5-hour and weekly limits sit in the menu bar.

Add a comment

Replies

Best
Hey Everyone! 👋 I'm Birju. I spend most of my day in Claude Code, and two things kept breaking my flow: hitting the 5-hour limit halfway through a task, and wanting to try other models without leaving the tool I already know. The fixes I found were a config file here, a router there, signing out and back in, restarting the session. So I built Moxie, a small Mac app that lives in the menu bar: • Use any AI with Claude Code: your ChatGPT plan, Gemini, DeepSeek, OpenRouter, or local models in Ollama. • Switch accounts mid-task. One click, and the same session keeps going on your other account. • See every account's 5-hour and weekly limits, with a heads-up before you run out. • It sets up Claude Code for you, in the CLI and the VS Code extension. Everything runs on your Mac. Keys stay in your Keychain, requests go straight to the provider you pick, and there's no Moxie account. It's free to try. I'd love your feedback: which model would you run Claude Code on first, and what's missing for your setup?

 Ive tried model hopping before. You get inconsistent results when you jump models. i run AI with months of calibrated feedback. swap the model tomorrow and the memory transfers but the reasoning resets. different weights, different floor.

the 11-models-behind-one-API play optimizes for cost. it sacrifices consistency. and consistency is where the real value compounds.

 Not really if you are switching to a on-par or higher model. Better yet, switch a claude account with another Claude account and get the same model handling it.

hitting the 5-hour wall mid-task is exactly the annoying part, so this is a real problem not a nice-to-have. when you switch accounts mid-task does the actual conversation context/history carry over to the new account, or does Claude Code just start a fresh session and you're re-explaining where you left off? that's the part that would decide whether this saves me time or just saves me the login dance.

 Claude Code technically has no idea that the account or model changed. It's session never got interrupted at all. It naturally transitions to the new account on next turn without realizing it. Moxie handles the handoff smoothly and carefully to not kill your ongoing requests and transition them to new account/model gracefully.

 that's a cleaner answer than I expected - sounds like Moxie sits below Claude Code at the transport/API layer rather than inside the session, so from the model's point of view nothing happened. that also means the thing Chris raised above is the real tradeoff, not the handoff mechanics: if you swap from Claude to a different model mid-task, the new model inherits the conversation history but not the judgment calls the first model was quietly making. does Moxie default to keeping you on the same model family when one account is low, and only cross to a different model as a last resort, or is it indifferent to which model picks up the thread?

 You control what model picks it up when you switch the account. It is only as smart as the model for judgement calls it makes. Moxie is facilitates the switch mechanism, you as a user control what model inherits it. So you can choose a on par or higher model or dumb it down, completely up to you.

 It does log requests locally and display them in the UI but those are just endpoints and statuses. Not bodies as it would slow down the system. It just passes streams through. It can be accomodated though. Feel free to provide that feedback or as a feature request at .