# looplj/axonhub

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

Repository: https://github.com/looplj/axonhub
Canonical: https://ross.abutalabs.com/products/axonhub
Homepage: https://axonhub.onrender.com/
Language: Go
License: NOASSERTION
License Family: other
Topics: ai, anthropic, openai, agent, agents, anthropic-api, api-gateway, cost-management, gemini-api, llm, claude, claude-code, codex, opencode, deepseek
Last push: 2026-08-26T05:09:16+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 85, longevity 25
- inputs: {"age_days": 358, "days_push": 7, "days_rel": 22, "gap_med": 1, "n_releases_24m": 116}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5078, forks 663 (observed 2026-08-28T04:09:09.485978+00:00)

## What it is
AxonHub is an open-source AI gateway written in Go that lets any SDK call 100+ LLMs through a unified API. It provides built-in failover, load balancing, cost control, and end-to-end tracing for LLM traffic.

## Use cases
- route openai sdk calls to claude gemini and deepseek models
- add failover and load balancing across multiple llm providers
- track and control llm api spending per project
- self-host an llm api gateway with tracing
- use claude code or codex with any model backend
- unify anthropic and openai apis behind one endpoint

## When to choose
- you need a self-hosted gateway to route LLM traffic across many providers with failover and cost tracking
- you want to use existing OpenAI/Anthropic SDKs against 100+ models without code changes

## When to avoid
- you only call a single LLM provider directly and don't need routing, failover, or cost control
- you need a fully managed cloud gateway rather than self-hosting

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, monitoring, tracing, rate-limiting, http-server
- domain: large-language-models, artificial-intelligence, apis, self-hosted, developer-tools
- platform: self-hosted, windows, go
- tags: ai-gateway, llm-proxy, failover, load-balancing, cost-control, openai-compatible, anthropic, multi-provider, ai-agents, docker, linux, macos, web-server

## Member repositories
- looplj/axonhub (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:09.485978+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:02:36.329110+00:00, confidence not recorded.
  - readme: https://github.com/looplj/axonhub (fetched 2026-08-28T04:09:09.485978+00:00, sha d4f9d755d257)
- Data as of 2026-08-30T08:39:29.467469+00:00.