# OpenRouterArchived/openrouter-runner

Deprecated inference engine

Repository: https://github.com/OpenRouterArchived/openrouter-runner
Canonical: https://ross.abutalabs.com/products/openrouter-runner
Homepage: https://openrouter.ai
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2025-09-06T13:41:32+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 40, release rhythm 35, longevity 78
- inputs: {"age_days": 1097, "days_push": 361, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1257, forks 125 (observed 2026-08-28T04:04:09.468830+00:00)

## What it is
A deprecated LLM inference engine built with vLLM by OpenRouter in its early days to serve niche fine-tuned models to early adopters. It is no longer in use and preserved only for historical purposes.

## Use cases
- serve fine-tuned LLMs with vllm
- self-host an OpenAI-compatible inference endpoint
- study how OpenRouter's early inference stack worked
- run a GPU model server for niche fine-tunes
- understand historical LLM provider infrastructure

## When to choose
- you need a historical reference for OpenRouter's early architecture
- you want a simple vLLM-based serving example to learn from

## When to avoid
- you need a production LLM inference server today
- you want current OpenRouter features like model routing or fallbacks
- you need maintained software with active support
- you want to serve the latest models via OpenRouter

## Facets
- artifact type: service
- maturity: abandoned
- function: llm-inference, http-server, api-framework
- domain: large-language-models, artificial-intelligence, self-hosted
- platform: python
- tags: vllm, deprecated, openrouter, historical, model-serving, inference-engine, gpu, docker, linux

## Member repositories
- OpenRouterArchived/openrouter-runner (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:09.468830+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 2026-08-30T05:07:10.389306+00:00, confidence not recorded.
  - readme: https://github.com/OpenRouterArchived/openrouter-runner (fetched 2026-08-28T04:04:09.468830+00:00, sha af8c302fbe9b)
  - homepage: https://openrouter.ai (fetched 2026-08-29T12:17:46.038536+00:00, sha f2b51360b517)
  - site_page: https://openrouter.ai/docs/quickstart (fetched 2026-08-29T12:17:46.047622+00:00, sha e8976457b1ef)
  - site_page: https://openrouter.ai/docs/features/uptime-optimization (fetched 2026-08-29T12:17:46.049504+00:00, sha 46bc4ca41ed2)
  - site_page: https://openrouter.ai/docs/guides/best-practices/uptime-optimization (fetched 2026-08-29T12:17:46.051179+00:00, sha b7e15b30298a)
  - site_page: https://openrouter.ai/docs/guides/routing/provider-selection (fetched 2026-08-29T12:17:46.052955+00:00, sha 389d2b80bd17)
  - site_page: https://openrouter.ai/docs/guides/privacy/provider-logging (fetched 2026-08-29T12:17:46.055285+00:00, sha 48ab9a52cc16)
  - site_page: https://openrouter.ai/about (fetched 2026-08-29T12:17:46.058701+00:00, sha e537c46a42df)
  - site_page: https://openrouter.ai/docs (fetched 2026-08-29T12:17:46.060114+00:00, sha 96995346ed15)
  - site_page: https://openrouter.ai/pricing (fetched 2026-08-29T12:17:46.056869+00:00, sha baa9001658a3)
- Data as of 2026-08-30T08:39:29.467469+00:00.