DevDock-AI/claude-unlimited

Rotate Claude and GPT subscriptions and API keys seamlessly inside the Claude Code CLI — switch on usage limits without interrupting your session, all from a local dashboard. 100% local.

What it solves

Claude Unlimited solves the problem of hitting usage limits while working in a Claude Code session. Normally, when you hit a limit, you must manually log out, log into a different account, and attempt to resume your work, which often results in lost context or session interruptions. This tool automates that handover, allowing you to pool multiple Claude, ChatGPT/Codex, and API accounts into a single, continuous session that never stops.

How it works

It runs a local daemon on your machine that acts as a router. When you initiate a request, the daemon intercepts it and selects an available account from your pool based on your configured priorities and usage thresholds. The rotation happens invisibly between requests, meaning your terminal session remains active and unaware that the underlying account has changed. Because it runs locally, your credentials are never stored in plaintext and never leave your machine; they are managed via your operating system's native secure storage.

Who it’s for

This tool is designed for power users and developers who rely heavily on Claude Code for coding tasks and frequently hit usage caps across their various AI subscriptions.

Highlights

  • Seamless rotation: Switches accounts automatically between requests without interrupting your terminal session.
  • Mixed account pooling: Combines Claude Pro/Max, ChatGPT/Codex, and API keys into one unified supply.
  • Local-first security: Operates entirely on your machine with no cloud components, telemetry, or external servers.
  • Dashboard control: Includes a local web dashboard for monitoring usage, costs, and managing account priorities.
  • Model parity: Allows you to map Claude models to specific GPT models when using Codex accounts.
  • Context preservation: Maintains your session context even when switching between different accounts in the pool.

Related

  • Project
    thushan/olla

    A high-performance LLM load balancer and proxy that intelligently routes requests across self-hosted inference nodes with automatic failover and health monitoring.

  • Project
    gpu-mode/reference-kernels

    A collection of reference GPU kernels and problem specifications used to evaluate and benchmark custom kernel implementations in GPU Mode competitions.

  • Project
    sybil-solutions/glm-flash-lite

    A serving stack that runs GLM-5.3-Flash (125 GB) on a single RTX 3090 24 GB by splitting its 12,096 routed experts across VRAM, RAM, and NVMe, delivering up to ~28 tok/s decode with near-exact output.

  • Project
    atopos31/llmio

    LLMIO is a Go-based LLM gateway that provides a unified API, weighted load balancing, and comprehensive observability for managing multiple AI model providers.