Awesome Infra for AI › LLM Gateways & Proxies

GetBusbar/busbar

⭐ 171 Rust added to this list on 2026-07-27 repository created 2026-05-29

Busbar is an open-source, self-hosted LLM gateway designed to sit between an application and various AI providers like OpenAI, Anthropic, Gemini, and Bedrock. It's built in Rust as a single, static binary, emphasizing high reliability and performance. The core functionality includes fault-attributed circuit breaking and streaming-safe in-flight failover, ensuring applications remain operational even if a provider experiences issues. Busbar translates seamlessly between different LLM wire protocols (chat, embeddings, images, audio, moderations), allowing applications to use one SDK (e.g., OpenAI's) while connecting to various backend providers. Key features include weighted pools with smooth round-robin load balancing, session affinity, and per-lane concurrency caps. It also offers flexible routing policies, either built-in, via dynamically loaded plugins, or through out-of-process sidecars, which can consider factors like cost, latency, concurrency, and rate limits. For security, Busbar provides native TLS/mTLS termination and hardening features like SSRF guards and constant-time authentication. Governance capabilities include signed expiring keys and hierarchical groups with configurable request, token, budget, and concurrency limits, along with spend tracking. Observability is provided through open standards like Prometheus metrics and OTLP traces. Busbar positions itself as a reliability-first alternative to other LLM gateways, focusing on robust operation and efficient multi-provider management for AI applications.

https://github.com/GetBusbar/busbar

ai-gatewayanthropicbedrockcircuit-breakerclaudefailovergeminilitellm-alternativellmllm-gatewayllm-proxyllmopsload-balanceropenaiopenrouter-alternativereverse-proxyrustsigv4streamingprotocol translationfault tolerancegovernanceobservability

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.