Awesome Infra for AI › LLM Gateways & Proxies

askalf/dario

⭐ 558 JavaScript added to this list on 2026-08-24 repository created 2026-04-08

dario is a local proxy that presents both OpenAI-compatible and Anthropic-compatible endpoints on one address and serves them from a Claude subscription rather than per-token API billing. Editors, agent frameworks and command line tools that speak either protocol point at the local endpoint and work unchanged. Every instance is a pool: signing in once creates a pool of one, and adding further seats makes the same local endpoint load-balance across them according to live remaining headroom, without a mode switch or configuration flag. Session-affinity routing keeps a given conversation pinned to the account that has been serving it, which matters for long agent runs where switching mid-session degrades continuity. Live drift detection watches for divergence between what the upstream returns and what clients expect, so protocol changes surface as a signal instead of as intermittent breakage. The tool ships as a single npm package with no runtime dependencies, releases are attested, and the project states that nothing is reported back to its authors. The codebase is deliberately small enough to audit, and the repository documents that it is an independent, unofficial third-party project rather than a vendor product. Recent releases removed a deprecated transport in favour of one request path and one credential model, simplifying what has to be reasoned about when debugging. dario belongs to a family of related self-hosting tools from the same author. It fits developers who already pay for a subscription plan and want the same entitlement available to every tool on their machine through a single stable local endpoint.

https://github.com/askalf/dario

llm-proxyanthropic-apiopenai-compatibleroutinglocal-firstjavascript

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.