# fawney19/Aether

Repository: https://github.com/fawney19/Aether
Canonical: https://ross.abutalabs.com/products/fawney19-aether
Homepage: https://fawney19.github.io/Aether/
Language: Rust
License: NOASSERTION
License Family: other
Last push: 2026-08-25T17:13:53+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 25
- inputs: {"age_days": 355, "days_push": 8, "days_rel": 15, "gap_med": 0, "n_releases_24m": 90}
- 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 1439, forks 212 (observed 2026-08-28T04:04:44.095126+00:00)

## What it is
Aether is a self-hosted AI API gateway written in Rust that provides a unified entry point for Claude, OpenAI, Gemini, and their CLI clients, with format conversion and forward/reverse proxying. It offers multi-tenant management, intelligent load balancing, cost quota control, and health monitoring, deployable via Docker Compose.

## Use cases
- unify claude openai gemini behind one api endpoint
- self-hosted llm api gateway with load balancing
- manage api keys and cost quotas for a team using ai services
- proxy claude code and other ai cli tools through a gateway
- convert between openai and anthropic api formats
- monitor health and usage of multiple llm providers

## When to choose
- you need a single unified API entry point for multiple LLM providers
- you want multi-tenant key management, quotas, and usage monitoring for a team
- you route AI CLI tools (Claude Code, etc.) through a controlled proxy
- you want a self-hosted alternative to commercial LLM routers

## When to avoid
- you only use a single LLM provider directly with no need for proxying or quotas
- you want a fully managed cloud service rather than self-hosting with Docker
- you need a lightweight client-side SDK rather than a server-side gateway

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, proxy, llm-inference, load-testing, monitoring, auth, self-hosted
- domain: large-language-models, apis, self-hosted, developer-tools, artificial-intelligence
- platform: self-hosted, rust
- tags: llm-gateway, multi-tenant, api-proxy, rate-limiting, cost-quota, claude, openai, gemini, reverse-proxy, docker, linux, web-server

## Member repositories
- fawney19/Aether (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:44.095126+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 2026-08-30T04:36:36.145132+00:00, confidence not recorded.
  - readme: https://github.com/fawney19/Aether (fetched 2026-08-28T04:04:44.095126+00:00, sha dc8e543edbd2)
  - homepage: https://fawney19.github.io/Aether/ (fetched 2026-08-29T11:46:56.736552+00:00, sha ebf594670082)
- Data as of 2026-08-30T08:39:29.467469+00:00.