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
ThinkWatchProject/ThinkWatch-Lite
ThinkWatch Lite is a Tauri 2 / React 19 desktop application for macOS, Windows and Linux that acts as a local LLM gateway sitting between AI coding clients and their model providers. Each client (Claude Code, Claude Desktop, Codex, opencode, Pi, Grok Build, Qwen Code, Hermes Agent, Zed, Aider, DeepSeek Harness, and others via manual instructions) is pointed at the gateway once, with its configuration file backed up and restorable; afterward, switching upstream providers or models happens centrally in the gateway rather than in each client. The gateway supports API keys, Amazon Bedrock, ChatGPT and Z.ai accounts, third-party relays such as OpenRouter, and local models, converting between the Anthropic, OpenAI and Gemini API formats. It adds routing rules based on model, tool use, images and extended thinking, with automatic failover to a healthy upstream and session pinning to preserve prompt-cache hits. Security features include outbound redaction of API keys, private keys, JWTs and other credentials before a request leaves the machine, and inspection of inbound tool calls to block ones that would download and execute code, exfiltrate credentials, or install persistence; a content filter also strips hidden-character prompt injection. It compares multiple upstreams serving the same declared model to flag inconsistent behavior, and scans MCP servers, skills, hooks and project instructions across thirteen supported clients for prompt injection, dangerous commands and overly broad permissions. Every request is logged with its matched rule, cost calculation and full text, searchable and replayable against a different upstream. Pricing is marked as estimated where exact cost data is unavailable. A remote core variant can run on a Linux server while the desktop app connects to it over an encrypted channel. The underlying gateway, ThinkWatch Core, is a separate open-source project bundled inside the app.
https://github.com/ThinkWatchProject/ThinkWatch-Lite
Also in LLM Gateways & Proxies
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.