razzant/claudexor

Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread...

View on GitHub ↗Jump to charts ↓Open shareable report →

razzant/claudexor has 500+ stars and 50+ forks on GitHub, is written in TypeScript, and was last pushed on Oct 18, 2026. Data as of . Signed-in members get hourly updates — create a free account.

Summary Information

Updated 37 minutes ago
Added to GitGenius on August 31st, 2026
Created on June 5th, 2026
Open Issues & Pull Requests: 92 (+1)
GitHub issues: Enabled
Number of forks: 54
Total Stargazers: 515 (+0)
Total Subscribers: 1 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 46.3 hours
Mean response time: 9.5 days
90th percentile: 31.6 days
Tracked items: 145

How this project is maintained

Roughly one issue in three opened in the past year never receives a reply. 48% of open issues come from outside the core team, a mix of external reports and the maintainers' own roadmap. Almost all tracked open issues have seen activity in the last three months. 60% of issues opened in the past year have been closed, leaving a working backlog. Three people close 99% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 83
New in 7 days: 6
Closed in 7 days: 2
Avg open age: 7 days
Stale 30+ days: 42
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1
Closed in 7 days: 1
Comments in 7 days: 2
Events in 7 days: 42

Top labels

  • bug (12)
  • enhancement (1)

Most active issues this week

Sign in to see which issues are moving.
Sign in

Detailed Description

Claudexor is a control plane for managing multiple AI coding assistants that enables quota-aware rotation across Claude Code, Codex, Cursor, and OpenCode subscriptions.

The tool solves the problem of hitting usage limits when relying on a single AI coding assistant subscription. It works by maintaining a shared thread context across multiple assistant instances and automatically rotating between them based on quota availability, allowing developers to continue working without interruption when one subscription reaches its limit. The system also enables cross-model code review, letting different AI assistants evaluate each other's output.

Claudexor suits developers who actively use multiple AI coding assistants and want to maximize their combined capacity without manual switching. It works as a local-first CLI tool and MCP server, making it suitable for developers who prefer command-line workflows and want to integrate AI assistance into their existing development environment. The project is particularly valuable for those managing multiple subscriptions across different platforms, as it abstracts away the complexity of tracking quotas and switching between services.

The project shows consistent development activity with regular commits addressing both feature additions and bug fixes. The codebase maintains active refinement of core functionality around quota management and context sharing. The tool receives ongoing attention to its integration points with multiple AI platforms, ensuring compatibility as those services evolve. Documentation and configuration handling are regularly updated to reflect new capabilities and improve user experience.