Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude...
opencodex is a lightweight local proxy that translates Codex's Responses API into the protocol used by a chosen provider, supporting streaming, tool calls, reasoning tokens, and images in both directions. It allows Codex, Claude Code, Claude Desktop, and Grok Build to run with Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Ollama, or other LLMs. The project provides a CLI and a web dashboard on localhost:10100 for configuration. Users can add providers from 40+ built-ins or any OpenAI-compatible endpoint, pick models, and manage accounts. opencodex can also manage a ChatGPT account pool for Codex auth, including adding multiple ChatGPT / Codex accounts and refreshing their 5h / weekly / 30d quota in the dashboard. Under quota routing, new sessions can use the lowest-usage healthy account, while round-robin and fill-first use their own policies. Existing Codex threads normally retain affinity to the account that started them. Additional
include combos that expose one virtual model id with failover or weighted round-robin across providers, sub-agents on any model, OAuth for xAI, Anthropic, and Kimi, and web search and vision sidecars for non-OpenAI models. The dashboard shows providers, OAuth status, model selection, and a live request log with cache token counts. A desktop app (beta) provides the same proxy and dashboard in a native window, and supported platforms include macOS, Linux, and Windows.
Developers use opencodex to run Codex, Claude Code, Claude Desktop, and Grok Build with any LLM they point it at.
Developers use opencodex to add providers and pick models through a web dashboard.
Developers use opencodex to pool ChatGPT accounts for Codex auth and refresh quotas.
Developers use opencodex to route new sessions to the lowest-usage healthy account under quota routing.
Developers use opencodex to create combos with failover or weighted round-robin across providers.
Developers use opencodex to feature routed models in Codex's sub-agent picker with fallback chains.
Developers use opencodex to give non-OpenAI models web search and image understanding through a sidecar.
✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go saves you more. Available on Web, iOS, macOS, Android, Linux, Windows. - ChatGPTNextWeb/NextChat
Discover Lorka, a multi-AI tool to combine GPT, Gemini, DeepSeek, and more in a single subscription. Fast, flexible, all-in-one AI.
Download DeskClaw — the easiest way to run OpenClaw AI agent on your desktop. No terminal, no config. Works on Windows & macOS. Free to start.
Official website restored from the pre-incident audit; product details pending editorial verification.