Open Source AI Gateways
An AI gateway sits between applications and AI services, providing a shared layer for sending requests to language models and other AI systems. It can unify access across providers, route requests to suitable models, and centralize controls such as authentication, rate limits, usage tracking, and fallback behavior. This helps teams manage integrations and costs while applying consistent policies without embedding provider-specific logic in every application.
Open source tools in this area include API proxies, model routers, and platforms for managing AI usage and access. When choosing one, consider its maturity, license, maintenance activity, deployment requirements, compatibility with your models and applications, and support for observability and governance. These tools can help developers, platform teams, and organizations that need to operate AI integrations across multiple services or environments.
7 repositories · updated September 28, 2026
Router: Optimize AI Model Selection and Costs for Agentic Systems
The Weave-OS Router is an intelligent model router for agentic systems, optimizing AI model selection for every request. It acts as a drop-in proxy for major AI providers, routing prompts to the most suitable model in under 50ms. This solution helps users significantly cut costs, often by 40-70%, simply by changing an endpoint.
A3M Router: Biology-Inspired LLM Routing for Cost Savings and Performance
A3M Router is an open-source, biology-inspired LLM router designed to optimize costs and performance across over 80 providers. It leverages principles like swarm intelligence and neural plasticity to offer adaptive, resilient, and cost-effective AI routing. This tool helps users save significantly on AI costs by intelligently selecting the best model for each query.
Otari: Self-Hosted OpenAI-Compatible LLM Gateway for 40+ Providers
Otari, from Mozilla AI, is an open-source, self-hosted LLM gateway. It provides a single OpenAI-compatible endpoint to connect with over 40 model providers, offering features like virtual keys, budget enforcement, and usage tracking. This solution empowers users to manage their AI stack with greater control and flexibility.
SandBase CLI: Connect Your AI Agent to 2,000+ Models and APIs
SandBase CLI is an open-source command-line interface and local MCP server that supercharges AI agents. It connects 25 popular AI clients, such as Claude Code, Cursor, and ChatGPT, to over 2,000 AI models and APIs, simplifying complex integrations. This powerful tool streamlines AI agent development by offering a unified gateway, removing the hassle of API key management and configuration.
OmniRoute: The Free AI Gateway for 350+ Providers and Coding Agents
OmniRoute is an open-source, MIT-licensed AI gateway designed to simplify access to a vast ecosystem of AI models and providers. It offers a single endpoint to connect with over 350 AI providers, including more than 150 free tiers, supporting 1200+ models from major labs like Kimi, Claude, GPT, and Gemini. This allows developers to streamline their AI workflows, leverage free resources, and integrate AI capabilities into their coding environments effortlessly.
Helicone: Open Source LLM Observability Platform and AI Gateway
Helicone is an open-source LLM observability platform and AI Gateway for AI engineers. It provides one-line code integration to monitor, evaluate, and experiment with large language models, offering features like cost tracking, prompt management, and intelligent routing. The platform supports a wide range of inference providers and frameworks, simplifying LLM development and deployment.
APIPark: Cloud-Native AI & API Gateway for LLM Management
APIPark is an open-source, cloud-native AI and API gateway designed for ultra-high performance and LLM API management. It simplifies the integration and deployment of over 100 AI models, offering a unified API, developer portal, and robust features for managing, monitoring, and securing AI services. This platform helps developers and enterprises accelerate their AI API development and build intelligent products or agents efficiently.