# Accenture/AmpliGraph

Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org

Repository: https://github.com/Accenture/AmpliGraph
Canonical: https://ross.abutalabs.com/products/ampligraph
Language: Python
License: Apache-2.0
License Family: permissive
Topics: machine-learning, knowledge-graph, relational-learning, representation-learning, graph-representation-learning, graph-embeddings, knowledge-graph-embeddings
Last push: 2026-08-06T22:50:36+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 60, longevity 100
- inputs: {"age_days": 2793, "days_push": 27, "days_rel": 58, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2238, forks 259 (observed 2026-08-28T04:06:29.574893+00:00)

## What it is
AmpliGraph is a Python library built on TensorFlow 2 for representation learning on knowledge graphs. It provides neural models (TransE, DistMult, ComplEx, HolE) that generate knowledge graph embeddings and predict missing links.

## Use cases
- predict missing links in a knowledge graph
- generate knowledge graph embeddings for entities and relations
- complete a large knowledge graph with new statements
- discover new facts from an existing knowledge graph
- cluster entities or find near-duplicates in a knowledge graph
- develop and evaluate custom relational learning models

## When to choose
- you need to train knowledge graph embedding models on GPU with TensorFlow
- you want link prediction and knowledge discovery APIs for RDF-like triple data
- you want a Keras-style extensible API to prototype new KG embedding models

## When to avoid
- you need a non-Python or PyTorch-based stack
- you only need graph analytics like centrality or shortest paths rather than embeddings
- you need a graph database or query engine rather than a machine learning library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning
- domain: machine-learning
- platform: python
- tags: knowledge-graph-embeddings, relational-learning, tensorflow, link-prediction, graph-representation-learning, embedding, knowledge-graphs, graph-embeddings, gpu

## Member repositories
- Accenture/AmpliGraph (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.574893+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 2026-08-30T02:44:12.300259+00:00, confidence not recorded.
  - readme: https://github.com/Accenture/AmpliGraph (fetched 2026-08-28T04:06:29.574893+00:00, sha 1bd36c976398)
  - registry_pypi: https://pypi.org/pypi/ampligraph/json (fetched 2026-08-29T10:24:38.609056+00:00, sha 29aae25b668c)
- Data as of 2026-08-30T08:39:29.467469+00:00.