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.
Awesome Infra for AI › LLM Gateways & Proxies
Casbin Gateway is a local, installable gateway and management console for the AI coding agents running on a developer's machine (Claude Code, Codex, Cursor, Gemini CLI, and many others). Installed with a single script, it runs as a background service with a tray icon and local web UI, requiring no external database, sign-in, or language runtime. It intercepts and relays traffic between each installed agent and up to 44 supported model providers (OpenAI, Anthropic, Google, and many third-party or self-hosted options such as Ollama, vLLM, and llama.cpp), letting a user point every agent at any provider from one place and switch, upgrade, or roll back agent versions centrally. Access-control policies, expressed and enforced through the Casbin authorization library, apply on every relayed request and can restrict roughly forty aspects of what each agent's tools, models, and providers are allowed to do. The gateway also gives visibility into what each agent is doing: it reads spend and usage directly from agents' own transcripts (including, on Windows, traffic that bypasses the proxy entirely), and it can probe a configured provider endpoint to check whether the model and features actually served match what was purchased, grading providers on an A-F authenticity scale. It also surfaces each agent's installed skills, MCP servers, and instruction files side by side, and supports copying these assets between agents. The project targets individuals or teams running multiple AI coding CLIs who want centralized routing, cost visibility, and policy control without modifying each agent.
https://github.com/apache/casbin-gateway
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.
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...
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.
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 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...
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 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.
OpenCodex is a universal local proxy that enables OpenAI Codex, Claude Code, and Grok Build to utilize any LLM provider, offering advanced model routing, account pooling, and API key management.