Awesome Infra for AI › LLM Gateways & Proxies

tiylabs/tiygate

⭐ 146 Rust added to this list on 2026-07-06 repository created 2026-06-17

TiyGate is a lightweight, open-source AI gateway written in Rust designed to unify access and management of various LLM providers such as OpenAI, Anthropic, Bedrock, and Gemini. It serves as a control plane sitting between applications and upstream LLM services, enabling users to consolidate fragmented provider access into a single interface. Key functionalities include policy-based routing of virtual models across different providers, automatic failover and recovery strategies based on criteria like priority, weight, throughput, and latency to ensure high availability. The gateway also provides detailed request/response logging, capturing interactions between the client, gateway, and provider, aiding in debugging and operational visibility. Furthermore, TiyGate aggregates usage analytics across various providers, models, and API keys, offering a clear overview of LLM consumption. It supports multiple protocols (OpenAI-compatible, Responses, Messages, Gemini) with extensible N\u00d7N protocol translation. Deployment options include a zero-config desktop app for personal use and containerized modes for enterprise-scale deployments with data plane/control plane separation. Security features include encryption of provider API keys at rest and redaction of sensitive log fields. TiyGate addresses the challenges of managing multiple LLM subscriptions, ensuring service reliability, simplifying debugging, and providing comprehensive usage insights in multi-provider LLM environments.

https://github.com/tiylabs/tiygate

ai-gatewayllm-gatewaymulti-provideropenai-compatiblefailovertraffic-managementllm-observabilityroutinglogging

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.

lidge-jun/opencodex

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.