Ghx

Ghx is a caching proxy for the GitHub CLI that eliminates redundant API calls and speeds up commands.

Ghx is a caching proxy designed for the GitHub CLI to eliminate redundant API calls and prevent rate limits. It is built specifically for AI agent workflows, allowing tools like Claude Code and GitHub Copilot to run faster without manual configuration. The daemon intercepts commands via a Unix socket, using context-aware keys and singleflight coalescing to share results among concurrent requests. Only allowlisted read-only commands are cached, while mutations pass through and invalidate related entries. It includes an in-memory cache, a real-time web dashboard, and a JSON API for monitoring.

Ghx at a glance

Best for: Software engineer, Designer
Runs on: macOS, Windows, Linux, Web
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: brunoborges.github.io

Key features

Caching proxy for GitHub CLI
Singleflight request coalescing
Allowlist-based command caching
Real-time web dashboard
JSON API for scripting
Unix socket communication
In-memory cache storage

Use it for

Speed up repeated GitHub CLI commands
Prevent API rate limits during AI agent workflows
Monitor cache hit rates and request logs
Share results among concurrent agent requests

Alternatives to Ghx

jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
CodeGraph — It eliminates file crawling, reducing AI agent tool calls by 88% and cutting costs.
uithub — Provides immediate full repository context for LLMs by changing one URL letter.
GitHub Copilot — Built into GitHub, with Claude and Codex agents on the same plan
OpenCodex — Runs Codex and Claude Code on over 40 language providers with zero client patches.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
FuXi — Runs as a single binary with automatic model routing and failover.
CLI Dispatch — Runs alternative AI models as workers from inside Claude Code.
fx — Minimal size and fast startup with zero background services.
oMLX — It uses paged SSD KV caching to reduce agent TTFT to under 5 seconds.
pstack — Improves AI coding agent outcomes with rigorous workflows.
Stoneforge — Runs isolated git worktrees and automated merges to prevent conflicts.

All Ghx alternatives