# OpenSPG/openspg

OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework.   Core Capabilities: 1) domain model constrained knowledge modeling, 2) facts and logic fused  representation, 3) natively support KAG...

Repository: https://github.com/OpenSPG/openspg
Canonical: https://ross.abutalabs.com/products/openspg
Homepage: https://spg.openkg.cn/en-US
Language: Java
License: Apache-2.0
License Family: permissive
Topics: knowledge-graph, knowledge-reasoning, spg, kag, knowledge-augmented-generation, llm-kg-bidirectional-enhancement
Last push: 2025-07-05T01:45:55+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 30, release rhythm 28, longevity 74
- inputs: {"age_days": 1045, "days_push": 425, "days_rel": 431, "gap_med": 46, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2217, forks 274 (observed 2026-08-28T04:06:27.257892+00:00)

## What it is
OpenSPG is a knowledge graph engine built on the SPG (Semantic-enhanced Programmable Graph) framework, developed by Ant Group with OpenKG. It provides semantic modeling, logical rule definitions, and construction/inference operator frameworks, and natively supports KAG (Knowledge Augmented Generation) for LLM-knowledge-graph bidirectional enhancement.

## Use cases
- build a domain knowledge graph from enterprise data
- combine LLMs with knowledge graphs for question answering
- model financial domain knowledge with semantic constraints
- run knowledge reasoning and inference over property graphs
- implement knowledge-augmented generation (KAG) pipelines
- convert messy incomplete data into evolving knowledge graphs

## When to choose
- you need industrial-grade knowledge graph construction with explicit semantics
- you want to fuse LLM reasoning with structured knowledge graphs
- you need pluggable adaptation of graph engines and algorithm services
- you work in finance or other domains requiring constrained knowledge modeling

## When to avoid
- you just need a simple property graph database without semantic modeling
- you want a lightweight RAG setup without graph infrastructure
- you need a fully turnkey managed service rather than a self-hosted engine

## Facets
- artifact type: framework
- maturity: active
- function: rag, nlp, llm-inference, database
- domain: large-language-models, databases, artificial-intelligence, fintech
- platform: python, jvm, self-hosted
- tags: knowledge-graph-engine, semantic-enhanced-programmable-graph, knowledge-augmented-generation, llm-kg-bidirectional-enhancement, graph-reasoning, ant-group, openkg, knowledge-graph, retrieval-augmented-generation, natural-language-processing, docker, linux, macos

## Member repositories
- OpenSPG/openspg (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:27.257892+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 2026-08-30T02:45:55.124732+00:00, confidence not recorded.
  - readme: https://github.com/OpenSPG/openspg (fetched 2026-08-28T04:06:27.257892+00:00, sha 3abc05e49124)
  - homepage: https://spg.openkg.cn/en-US (fetched 2026-08-29T10:26:03.667333+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.