cheapestinference/claude-auto-retry

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based

What it solves

claude-auto-retry is a utility that prevents productivity loss when using Claude Code (the CLI tool) by automatically resuming sessions that have been paused by Anthropic's subscription rate limits, API overloads, or transient errors. It eliminates the need for users to manually monitor the terminal and type "continue" once a limit resets.

How it works

The tool operates as a shell function wrapper around the claude command. It uses tmux to keep the session running in the background, even if the user disconnects or the laptop sleeps. A background monitor polls the tmux pane every 5 seconds to detect specific error messages in the terminal output.

Depending on the message detected, it triggers different recovery paths:

  • Usage Limits: Parses the reset time (timezone-aware) and sends "continue" after the reset plus a 60-second margin.
  • API Overload: Implements an exponential backoff with jitter for 5xx errors or overloaded_error responses.
  • Safeguard False Positives: Performs a bounded number of immediate re-sends to clear transient AUP flags.
  • Interrupted Streams: Resumes work when a connection is dropped or the computer sleeps mid-response.

Who it’s for

Developers using the Claude Code CLI who run long-running tasks, overnight jobs, or agentic workflows that are frequently interrupted by rate limits or API instability.

Highlights

  • Zero Workflow Change: Integrates as a replacement for the claude command with the same TUI experience.
  • Tmux Integration: Automatically creates and manages tmux sessions to ensure persistence across SSH drops or system sleeps.
  • Timezone-Aware Parsing: Accurately handles IANA timezone offsets and Daylight Saving Time transitions when calculating reset times.
  • Event-Driven Detection: Optional StopFailure hook for ambiguity-free overload detection without terminal scraping.
  • Chrome-Aware Scraping: Intelligent terminal monitoring that ignores UI elements like the input box and status spinners to avoid false positives.
  • Pure Node.js: No external node_modules dependencies.

Related

  • Project
    richhickson/claudecodeusage

    Claude Usage is a native macOS menubar app that shows real‑time Claude Code quota usage (session, weekly, monthly) and alerts you when a Claude Code session is waiting for input, letting you jump directly to the terminal tab. It reads your OAuth token from the Keychain, polls Anthropic’s usage endpoint, and uses Claude Code’s hook system for session monitoring.

  • Project
    wesammustafa/Claude-Code-Everything-You-Need-to-Know

    A thorough, example‑rich tutorial for Anthropic’s Claude Code CLI, covering installation, prompt engineering, and advanced extensions (Skills, Hooks, Sub‑agents, Workflows, MCP) to let developers use Claude for repo‑wide code analysis, editing, testing and automation.

  • Project
    kristianvast/hermes-claude-auth

    hermes‑claude‑auth is a Python runtime patch that lets the hermes‑agent use a Claude Code subscription after Anthropic added OAuth validation. It installs a .pth shim that monkey‑patches the agent’s request builder, adds the required billing header, fixes prompt layout, and implements auto‑wait for subscription‑window rate limits. The installer works on Linux/macOS and Windows, provides uninstall scripts, and includes git‑hook + cron recovery to survive hermes updates.

  • Dispatch
    Claude Code Best Practices Guide

    Anthropic provides a comprehensive set of best practices for optimizing Claude Code, an agentic coding environment, focusing on context window management and autonomous verification.

  • Project
    frankbria/ralph-claude-code

    An autonomous development loop for Claude Code that iteratively implements project requirements with built-in safeguards against infinite loops and API overuse.