opencodex
Reduces vendor lock-in by routing Codex and Claude Code requests to any LLM backend, enabling cost optimization and model experimentation without rewriting i…
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
- Ask Claude to complete code snippets using your existing Codex CLI without switching tools.
- Generate function implementations with DeepSeek or Gemini through a unified code interface.
- Automate multi-LLM testing of code generation across Claude, Grok, and local Ollama models.
Reduces vendor lock-in by routing Codex and Claude Code requests to any LLM backend, enabling cost optimization and model experimentation without rewriting integrations.
Engineering teams invested in Codex tooling seeking flexibility to switch or blend LLM providers without infrastructure refactoring.
https://github.com/lidge-jun/opencodex
By lidge-jun
How to Get It
claude plugins install lidge-jun/opencodex
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Complete code snippets using my existing Codex CLI without switching tools
Trust Signals Auto-scanned
Community Pulse New
- Show HN: Open Codex – OpenAI Codex CLI with open-source LLMs — Hacker News · 106 pts
- Proxy for OpenAI Codex and Claude Code, use any LLM with those apps — Hacker News · 6 pts
- OpenCodex – A developer hub to showcase projects and profiles — Hacker News · 1 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 3,879 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 3,879 GitHub stars; contributors unknown; last commit 0d ago; license MIT.