lidge-jun/opencodex Alternatives

LLM provider proxy/gateway for AI coding agents

A lightweight local provider proxy that lets OpenAI Codex, Claude Code, Claude Desktop, and Grok Build use any LLM backend, translating Codex/Anthropic protocols to provider APIs and optionally managing ChatGPT account pools for Codex.

15.5kTypeScriptMITactive · last push 16d agoGitHub

Drop-in peers

Same problem, same approach. Swapping one for another is a config change, not a rewrite.

Sort

diegosouzapw/OmniRouteGitHub

same class; choose when you need an all-in-one gateway with hundreds of providers and multi-agent support rather than seed's focused Codex/Claude translation.

Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by hundreds of contributors

: 72.7k
: TypeScript
: MIT

active4d ago

musistudio/claude-code-routerGitHub

same class; choose when you need a local control plane with model routing and fusion, not just protocol translation.

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

: 37.2k
: TypeScript
: MIT

active22d ago

justlovemaki/AIClient2APIGitHub

same class; choose when you need multi-protocol conversion across Antigravity, Codex, Grok, Kiro, Claude, and custom providers.

Self-hosted multi-protocol AI API proxy for Antigravity, Codex, Grok, Kiro, OpenAI, Claude, and custom providers. Supports OpenAI-compatible API, Claude API, Gemini protocol conversion, GPT, Grok Build, Claude Opus, Gemini Pro, Kimi, MiniMax, provider pools, smart routing, and automatic failover.

: 8.8k
: JavaScript
: GPL-3.0

active20d ago

decolua/9routerGitHub

same class; choose when your priority is free provider access and automatic failover over supporting every model family.

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

: 29.4k
: JavaScript
: MIT

active18d ago

kittors/CliRelayGitHub

same class; choose when you want a coding-CLI gateway with management console, traces, and quota limits built in.

Self-hosted AI gateway for coding CLIs — one OpenAI/Claude/Gemini/Codex-compatible endpoint, with a multi-tenant web console, request logs, and spend quotas.

: 1.0k
: Go
: MIT

active17d ago

caozhiyuan/copilot-apiGitHub

same class; choose when you need Copilot/Codex subscription backends exposed through OpenAI/Anthropic-compatible APIs.

GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.

: 1.0k
: TypeScript
: MIT

active17d ago

Same job, different approach

Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.

BeehiveInnovations/pal-mcp-serverGitHub

MCP-server-based abstraction layer for using coding CLIs with many providers; choose when you work in an MCP tool ecosystem rather than an HTTP proxy.

The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.

: 11.8k
: Python
: NOASSERTION

slowing10mo ago

Listed as an alternative to

These projects were analysed and named opencodex among their alternatives. The relationship is not symmetric — how opencodex rates them is a separate judgement, made when opencodex is analysed in its own right.

decolua/9routerGitHub

calls opencodex “Use it when the clients you must support are Codex and Claude Code and you want a lightweight universal provider proxy for any LLM.”

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

29.4kJavaScriptactive

justlovemaki/AIClient2APIGitHub

calls opencodex “Focuses on exposing Codex CLI/SDK to any LLM via a universal proxy; choose when Codex is your primary client.”

8.8kJavaScriptactive

BerriAI/litellmGitHub

calls opencodex “when your clients are Codex/Claude Code and you want provider-agnostic protocol translation”

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

60.1kPythonactive

router-for-me/CLIProxyAPIGitHub

calls opencodex “Choose when you want a TypeScript control point that lets Codex/Claude Code clients use arbitrary upstream API providers instead of exposing CLI logins to API clients.”

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Davin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API

52.5kGoactive

BlockRunAI/ClawRouterGitHub

calls opencodex “Use it to point Codex CLI/App/SDK at arbitrary providers including Ollama; it assumes Codex as the client, not a generic router API.”

The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

6.6kTypeScriptactive

diegosouzapw/OmniRouteGitHub

calls opencodex “Current TypeScript proxy for Codex and Claude Code, narrower than OmniRoute because it leaves provider aggregation and fallback to your own config.”

72.7kTypeScriptactive

chatanywhere/GPT_API_freeGitHub

calls opencodex “Choose when you use Codex CLI/App/SDK or Claude Code and want to route arbitrary LLMs through one local proxy.”

免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！

42.9kactive

musistudio/claude-code-routerGitHub

calls opencodex “Choose when you only work with Codex CLI and Claude Code and want a minimal proxy for external models over CCR's broader agent roster.”

One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.

37.2kTypeScriptactive

maximhq/bifrostGitHub

calls opencodex “when you need to point Codex/Claude Code CLIs at arbitrary models, not to serve production traffic.”

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

8.2kGoactive