looplj/axonhub

⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end tracing.

What it solves

AxonHub is an AI gateway designed to eliminate vendor lock-in and reduce integration complexity. It allows developers to switch between different AI model providers (such as OpenAI, Anthropic, Gemini, and DeepSeek) without changing their application code, by providing a unified API translation layer.

How it works

AxonHub acts as a transparent proxy between the application and various AI providers. It translates requests from one SDK (e.g., OpenAI SDK) into the format required by another provider (e.g., Anthropic), enabling "Any SDK $\rightarrow$ Any Model" connectivity. It includes a management dashboard for configuring AI channels, tracking costs, and monitoring requests.

Who it’s for

It is built for developers and enterprise teams who want to maintain flexibility in their AI stack, avoid being tied to a single provider, and simplify the management of multiple AI APIs across different modalities.

Highlights

  • Unified API Translation: Use the OpenAI SDK to call Claude, or the Anthropic SDK to call GPT, with zero code changes.
  • Observability: Built-in full request tracing with thread-aware timelines for faster debugging.
  • Enterprise Management: Features fine-grained RBAC (Role-Based Access Control), usage quotas, and data isolation.
  • Reliability: Smart load balancing with auto-failover in under 100ms to ensure high availability.
  • Cost Control: Real-time tracking of input, output, and cache tokens with per-request cost breakdowns.
  • Broad Provider Support: Compatible with OpenAI, Anthropic, Gemini, DeepSeek, Zhipu AI, and others.