# thunlp/OpenKE

An Open-Source Package for Knowledge Embedding (KE)

Repository: https://github.com/thunlp/OpenKE
Canonical: https://ross.abutalabs.com/products/openke
Language: Python
License Family: other
Topics: knowledge-embedding
Last push: 2024-01-10T11:51:05+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3251, "days_push": 966, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4047, forks 986 (observed 2026-08-28T04:08:33.731574+00:00)

## What it is
OpenKE is an open-source PyTorch-based toolkit for knowledge graph embedding (knowledge representation learning), with C++ accelerated data preprocessing and negative sampling. It implements classic models such as TransE, TransH, TransR, TransD, DistMult, ComplEx, RotatE, RESCAL, and SimplE, plus TensorFlow and lightweight C++ inference variants.

## Use cases
- train knowledge graph embedding models
- run link prediction on knowledge graphs
- compute entity and relation embeddings for a knowledge base
- benchmark TransE, TransR, RotatE and other KRL models
- use knowledge embeddings for downstream NLP tasks

## When to choose
- you need a well-established PyTorch framework for knowledge graph embedding research
- you want implementations of many classic KRL models in one toolkit
- you need GPU-accelerated training on large-scale knowledge graphs

## When to avoid
- you need actively maintained code with recent bug fixes or a permissive license
- you want modern state-of-the-art embedding models beyond the classic TransX family
- you need a production system rather than a research toolkit

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning
- platform: python, cross-platform
- tags: knowledge-graph, knowledge-embedding, pytorch, link-prediction, knowledge-representation-learning, transe, rotate, research, natural-language-processing, algorithms, gpu, linux

## Member repositories
- thunlp/OpenKE (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:33.731574+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 2026-08-29T18:23:42.802137+00:00, confidence not recorded.
  - readme: https://github.com/thunlp/OpenKE (fetched 2026-08-28T04:08:33.731574+00:00, sha f067d65fdd56)
- Data as of 2026-08-30T08:39:29.467469+00:00.