benedictking/ccx

Claude / Codex / Gemini API Proxy - CCX

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 17th, 2026
Created on January 31st, 2026
Open Issues & Pull Requests: 31 (+0)
GitHub issues: Enabled
Number of forks: 323
Total Stargazers: 3,988 (+0)
Total Subscribers: 15 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 5.1 hours
Mean response time: 21.0 hours
90th percentile: 39.1 hours
Tracked items: 250

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Practically every issue opened in the past year has drawn a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 88% of issues opened in the past year have been closed, leaving a working backlog. Three people close 77% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 31
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 57 days
Stale 30+ days: 20
Stale 90+ days: 0

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 1
Events in 7 days: 2

Top labels

No label distribution available yet.

Detailed Description

CCX is an API proxy and protocol translation gateway that unifies access to Claude, OpenAI Chat, OpenAI Images, OpenAI Embeddings, Codex, and Gemini APIs.

The tool solves the problem of managing multiple AI API providers and keys across different services. It acts as a central gateway that translates requests to the appropriate backend API format, allowing applications to switch between providers or distribute load across them without changing client code. The proxy includes built-in channel orchestration with failover support, meaning if one API provider becomes unavailable, requests automatically route to another configured channel. It offers smart scheduling with priority-based routing, health checks, and circuit recovery to maintain reliability.

Teams managing multiple AI API integrations or needing to switch providers should consider this tool. It suits projects that require high availability across multiple AI services, need to rotate API keys for security or quota management, or want to test different models and providers without application-level changes. The web administration console provides visibility into channel health, request logs, and testing capabilities, making it useful for operations teams monitoring API usage. The tool's support for context routing filters ensures requests go to channels capable of handling the required model context window and output length.

The project maintains a substantial base of adopters who report issues from real-world use rather than the core team driving the issue backlog. Maintainers typically respond to new issues and pull requests within a day, indicating active engagement with the community.