bestruirui/octopus

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

What it solves

Octopus is an LLM API aggregation service designed for individuals who use multiple AI providers. It eliminates the need to manage multiple API keys and different API formats, providing a unified interface for accessing various models while ensuring high availability through automatic failover.

How it works

The service acts as a proxy between the client and multiple LLM providers. It converts protocols between OpenAI, Anthropic, and Gemini formats and aggregates multiple provider channels into "groups" (unified model names). It also tracks token consumption and costs by syncing pricing data from external sources like models.dev.

Who it’s for

  • Individuals managing multiple LLM API keys across different providers.
  • Developers who want a single, stable endpoint for their AI agents or applications.
  • Users who want to track their total AI spending across different channels.

Highlights

  • Multi-Channel Aggregation: Connect and manage multiple LLM providers in one place.
  • Protocol Conversion: Seamlessly switch between OpenAI and Anthropic API formats.
  • Automatic Failover: Automatically switches to a working channel if an upstream provider fails.
  • Real-Time Visualization: View the complete request path from client to provider in the frontend.
  • Lightweight Deployment: Deploys as a single binary with support for SQLite, MySQL, and PostgreSQL.

Related

  • Project
    theopenco/llmgateway

    LLM Gateway is an open‑source API gateway that provides a single OpenAI‑compatible endpoint for routing requests to multiple LLM providers, centralising API‑key management and offering built‑in usage and performance analytics. It can be used as a hosted SaaS service or self‑hosted via Docker.

  • Project
    atopos31/llmio

    A Go-based LLM load-balancing gateway that provides a unified REST API, weighted scheduling, and detailed observability for multiple AI providers.

  • Project
    yym68686/uni-api

    uni‑api is a config‑only server that presents a single OpenAI‑compatible API while routing calls to many LLM providers (OpenAI, Anthropic, Gemini, Vertex, Azure, AWS, etc.). It supports weighted and round‑robin load balancing, automatic retries, per‑model timeouts, rate limits, tool‑call passthrough, content moderation, and fine‑grained request overrides—all defined in an `api.yaml` file or via a `CONFIG_URL`. Deployable as a Docker container (one‑click Fugue button provided).

  • Project
    fruitbars/simple-one-api

    simple‑one‑api is an open‑source Go gateway that unifies multiple LLM providers behind OpenAI‑compatible endpoints, adds capacity‑aware key scheduling, four‑layer rate‑limiting, a built‑in React chat UI, a visual config console, and a Wails desktop client. It can be run as a single binary, Docker container, or desktop app, and stores its configuration in SQLite.

  • Project
    mozilla-ai/otari

    An OpenAI-compatible LLM gateway that provides a unified endpoint for multiple providers, enabling centralized credential management, budget enforcement, and usage tracking.