Accenture/AmpliGraph

Health v2 · maintenance only

Adoption not part of the score

2242 stars · 257 forks observed · 2026-10-06

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity active

machine-learning machine-learning python knowledge-graph-embeddings relational-learning tensorflow link-prediction graph-representation-learning embedding knowledge-graphs graph-embeddings gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Accenture/AmpliGraph")