# bestruirui/octopus

One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

Repository: https://github.com/bestruirui/octopus
Canonical: https://ross.abutalabs.com/products/bestruirui-octopus
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: ai, ai-gateway, anthropic, claude, claude-code, codex, openai, self-hosted, llm-gateway, codex-app, codex-cli, codex-desktop, opencode, pi
Last push: 2026-08-26T07:30:38+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 20
- inputs: {"age_days": 289, "days_push": 7, "days_rel": 8, "gap_med": 0, "n_releases_24m": 80}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2527, forks 399 (observed 2026-08-28T04:06:58.540516+00:00)

## What it is
Octopus is a self-hosted LLM API aggregation gateway that unifies multiple provider channels behind a single endpoint, converting between OpenAI Chat, OpenAI Responses, and Anthropic API formats. It includes automatic failover, model and price syncing, request visualization, and usage analytics with a web management panel.

## Use cases
- aggregate multiple llm providers behind one api endpoint
- convert anthropic api requests to openai format
- self-host an openai-compatible gateway for claude code and codex
- add automatic failover when an llm provider goes down
- track token usage and cost across llm channels
- shield agent tasks from upstream llm errors

## When to choose
- you use multiple LLM providers and want one unified API
- you need protocol conversion between OpenAI and Anthropic formats
- you want a lightweight single-binary or Docker self-hosted gateway
- you need per-request analytics, cost tracking, and failover for LLM traffic

## When to avoid
- you need enterprise-grade multi-tenant API management at scale
- you want a fully managed cloud gateway without self-hosting
- you only call a single LLM provider directly
- you need fine-grained team quota and billing features beyond personal use

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, proxy, middleware, analytics, monitoring
- domain: large-language-models, apis, self-hosted, backend
- platform: self-hosted, windows, go
- tags: llm-gateway, api-aggregation, openai-compatible, anthropic, protocol-conversion, failover, claude-code, codex, ai-agents, docker, web-server, linux, macos

## Member repositories
- bestruirui/octopus (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.540516+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 2026-08-30T02:25:24.473537+00:00, confidence not recorded.
  - readme: https://github.com/bestruirui/octopus (fetched 2026-08-28T04:06:58.540516+00:00, sha c404462d41a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.