Awesome Infra for AI › LLM Gateways & Proxies

lidge-jun/opencodex

⭐ 16932 TypeScript added to this list on 2026-07-27 repository created 2026-06-18

OpenCodex is a powerful local proxy designed to make the OpenAI Codex, Claude Code, and Grok Build platforms more versatile by allowing them to work with a wide range of LLM providers beyond their native integrations. It acts as an intermediary, translating the application's API requests into the format required by different LLM backends such as Claude, Gemini, Grok, DeepSeek, Ollama, and many others. This ensures that users can leverage their preferred models without waiting for official support. The proxy handles various functionalities including streaming responses, tool calls, and image handling, ensuring seamless operation in both directions. A key feature of OpenCodex is its ability to manage a pool of ChatGPT/Codex accounts, automatically routing new sessions to the lowest-usage healthy account, and refreshing quotas. This is particularly useful for managing API limits and ensuring continuous service. It also supports pinning existing threads to the account that initiated them to maintain context. Configuration and provider management are streamlined through an interactive CLI setup or a web-based dashboard, which allows users to add over 40 built-in providers or custom OpenAI-compatible endpoints. The system also auto-discovers models and provides flexible model routing using a `provider/model` syntax, even aliasing model IDs with slashes for compatibility. OpenCodex is designed for ease of installation and works across macOS, Linux, and Windows, bundling the Bun runtime for simplified deployment.

https://github.com/lidge-jun/opencodex

LLM proxyAI gatewaymodel routingOpenAI CodexClaude CodeGrok BuildLLM provider integrationAPI key managementaccount poolinginferencelocal proxy

Also in LLM Gateways & Proxies

diegosouzapw/OmniRoute

OmniRoute is a free AI gateway that unifies access to over 170 AI providers, offering token compression, auto-fallback, and aggregating free tiers to provide billions of free tokens monthly.

Mintplex-Labs/anything-llm

AnythingLLM is an all-in-one local-first AI application for chatting with documents, managing AI agents, and integrating with various LLMs and vector databases, offering dynamic model routing and m...

BerriAI/litellm

LiteLLM is an open-source AI Gateway and Python SDK providing a unified interface to over 100 LLM providers, with features like cost tracking, guardrails, load balancing, and observability.

QuantumNous/new-api

new-api is a unified LLM gateway and AI asset management system that enables aggregation, distribution, and cross-conversion of various LLMs into OpenAI, Claude, or Gemini compatible formats, offer...

Kong/kong

Kong Gateway is a cloud-native API and AI gateway offering high performance, extensibility via plugins, and advanced AI traffic capabilities including multi-LLM support, semantic security, and cach...

decolua/9router

9Router is an AI router and token saver that connects various AI coding tools to over 40 AI providers, optimizing usage with auto-fallback, quota tracking, and token compression.

apache/apisix

Apache APISIX is a dynamic, real-time, high-performance API Gateway that can also function as an AI Gateway, providing AI proxying, load balancing for LLMs, and robust security for AI agents.

casdoor/casdoor

Casdoor is an open-source, "AI-first" Identity and Access Management (IAM) and Model Context Protocol (MCP) gateway, providing authentication and authorization for AI applications and agents.