Categories
Self-Hosted Developer Tools AI Gateway API Management LLM Proxy Model Routing Cost Management LLM ObservabilityStars
Forks
Watchers
Developer links
AxonHub
AxonHub is an open-source AI gateway that lets any OpenAI, Anthropic, or Gemini SDK reach more than 100 models through a single address. Point Claude Code, Codex, OpenCode, or your own scripts at one base URL, and the gateway translates each request for whichever provider sits behind the model name, so changing vendors means editing a string instead of rewriting code. Channels hold provider keys, model lists, weights, and health history, and load balancing with automatic failover sends traffic to the healthiest route. Chat, image generation, embeddings, and reranking all travel through the same endpoint. Every call lands in request logs with token counts, first-token latency, and cost, and traces group related calls into threads with a timeline of spans. A built-in playground tests one channel or the full gateway, prompt protection rules filter sensitive text before it leaves your network, and API keys can be limited by project, owner, or IP range. Roles and per-user usage tables keep teams apart. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.
Benefits
- Switch Providers Without Code Changes
- Keep the SDK you already use and change only the model name, because the gateway translates requests between OpenAI, Anthropic, Gemini, and other formats for you.
- Stay Online When Providers Fail
- Weighted load balancing and automatic failover route each request to a healthy channel, so one rate limit or outage does not take down your applications.
- See Every Call In Detail
- Request logs, traces, and threads show models, tokens, timing, and cost for each call, which makes slow or expensive prompts easy to find and fix.
- Control Who Spends What
- Separate projects, personal and service keys, roles, and per-user usage tables let administrators share one set of provider credentials safely across a whole team.
Features
- Any SDK, Any Model
- Call Claude with the OpenAI SDK or GPT with the Anthropic SDK, using compatible OpenAI, Anthropic, and Gemini endpoints for text, images, embeddings, and rerank.
- Channel Management
- Add providers with keys, base URLs, and model lists, fetch available models in one click, test the connection, and enable each channel when ready.
- Request Tracing
- Send a trace or thread ID header and review a timeline of spans, prompts, responses, and token counts for every model call in that conversation.
- Usage Dashboard
- Watch request counts, success rate, token totals, and per-channel health on a dashboard, then drill into usage statistics by user.
- Prompt Protection Rules
- Define rules that detect and filter sensitive information in prompts before they are forwarded to any external model provider.
- Built-In Playground
- Chat with a single channel or the whole gateway, adjust temperature, token limits, and system prompt, and confirm a setup works before connecting clients.