# romgX/openrelay

几百个免费 AI 模型配额，一键接入本地项目。| Hundreds of free AI model quotas, one-click access to local projects.

Repository: https://github.com/romgX/openrelay
Canonical: https://ross.abutalabs.com/products/openrelay
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, ai-proxy, claude, claude-code, cursor, developer-tools, kiro, openai, proxy, windsurf, openclaw, aider, cerebras, copilot, free-ai, free-api, groq, llm-proxy, model-router
Last push: 2026-08-12T10:24:55+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 97, release rhythm 85, longevity 12
- inputs: {"age_days": 179, "days_push": 21, "days_rel": 21, "gap_med": 0.0, "n_releases_24m": 81}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2286, forks 320 (observed 2026-08-28T04:06:34.109851+00:00)

## What it is
OpenRelay is a desktop application that aggregates AI model quotas from local tools (Claude Desktop, Kiro, Windsurf, Copilot, etc.) and direct API providers (Groq, Cerebras, Gemini, DeepSeek, Ollama, etc.) behind a single local OpenAI/Anthropic-compatible endpoint. It includes a web panel for one-click configuration of CLI tools like Claude Code, Aider, and Goose, with custom model groups and automatic failover.

## Use cases
- use my Claude Pro subscription quota in Aider or Claude Code
- route Cursor and Windsurf through a local LLM proxy
- aggregate free AI API quotas from Groq and Cerebras in one endpoint
- set up failover between multiple AI model providers
- one-click configure environment variables for AI CLI tools
- expose Claude Desktop quota to any Anthropic-compatible tool
- manage all my AI provider quotas from a single dashboard

## When to choose
- you have multiple AI subscriptions or free quotas locked to specific tools and want to reuse them anywhere
- you use AI coding CLIs (Claude Code, Aider, Goose) and want one-click provider switching
- you want a local OpenAI/Anthropic-compatible proxy with automatic failover across providers

## When to avoid
- you need a production-grade, multi-tenant API gateway for a team or company
- you only use a single provider and don't need quota aggregation
- you require fully open-source software, since OpenRelay uses an Open Core license

## Facets
- artifact type: application
- maturity: active
- function: proxy, llm-inference, api-gateway, developer-tools, chatbot
- domain: large-language-models, developer-tools, artificial-intelligence, self-hosted
- platform: windows, cross-platform, self-hosted
- tags: llm-proxy, model-router, free-ai-quotas, claude-code, aider, cursor, openai-compatible, provider-aggregation, failover, macos, linux

## Member repositories
- romgX/openrelay (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:34.109851+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 2026-08-30T02:40:54.036500+00:00, confidence not recorded.
  - readme: https://github.com/romgX/openrelay (fetched 2026-08-28T04:06:34.109851+00:00, sha c8f4205892f6)
- Data as of 2026-08-30T08:39:29.467469+00:00.