# AkaliKong/MiniOneRec

Minimal reproduction of OneRec

Repository: https://github.com/AkaliKong/MiniOneRec
Canonical: https://ross.abutalabs.com/products/minionerec
Language: Python
License: Apache-2.0
License Family: permissive
Topics: generative-ai, generative-recommendation, generative-recommenders, large-language-model, large-language-models, llm, recommendation, recommendation-system, recommender-system, scaling-laws
Last push: 2026-05-14T15:56:06+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 82, release rhythm 35, longevity 22
- inputs: {"age_days": 316, "days_push": 111, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1770, forks 257 (observed 2026-08-28T04:05:33.860653+00:00)

## What it is
MiniOneRec is an open-source framework for generative recommendation built on large language models, covering the full pipeline of semantic ID (SID) construction, supervised fine-tuning, and recommendation-oriented reinforcement learning. It is a minimal reproduction of the OneRec system intended for research and experimentation with LLM-based recommenders.

## Use cases
- reproduce generative recommendation with llms
- train a recommender system using sft and reinforcement learning
- build semantic ids for items with rq-kmeans
- experiment with scaling laws for generative recommenders
- fine-tune qwen models for recommendation tasks
- evaluate llm-based recommendation with constrained decoding

## When to choose
- you want an end-to-end open-source generative recommendation pipeline
- you are researching llm-based or generative recommender systems
- you need reproducible OneRec-style training including SID construction and RL

## When to avoid
- you need a production-ready recommendation service with low-latency serving
- you want a traditional collaborative filtering recommender without llms
- you lack GPU resources for fine-tuning large language models

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, llm-training, reinforcement-learning, rag
- domain: machine-learning, large-language-models, artificial-intelligence, developer-tools
- platform: python
- tags: generative-recommendation, recommender-system, sid-construction, sft, scaling-laws, llm-based-recommendation, gpu, linux

## Member repositories
- AkaliKong/MiniOneRec (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:33.860653+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 2026-08-30T03:26:01.958733+00:00, confidence not recorded.
  - readme: https://github.com/AkaliKong/MiniOneRec (fetched 2026-08-28T04:05:33.860653+00:00, sha 546502d60bfd)
- Data as of 2026-08-30T08:39:29.467469+00:00.