OpenSPG/KAG

LLM Frameworks

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.

GitHub →Website →

6.7

GitHub Metrics

Stars

8.9k

Forks

692

Open Issues

173

Watchers

Contributors

Weekly Commits

Language

Python

License

Apache-2.0

Last Commit

Jan 28, 2026

Created

Sep 21, 2024

Latest Release

v0.8.0

Release Date

Jun 28, 2025

Synced: Jun 29, 2026

Quality Scores

Documentation Qualityw: 20%

7.7

Has docs site (https://spg.openkg.cn/en-US). Description: 307 chars. Stars signal: 8,855. Contributors: 25. Score: 7.7/10

Community Healthw: 20%

6.9

Stars: 8,855. Contributors: 25. Watchers: 73. Forks: 692. Issue ratio: 2.0%. Score: 6.9/10

Maintenance Velocityw: 15%

3.5

Last commit: 151d ago. Weekly commits: 0. Latest release: v0.8.0. Maturity bonus: 1.8y old. Score: 3.5/10

API Design & DXw: 20%

7.9

Stars/issues ratio: 51. Dynamic language: Python. Has documentation site. Permissive license: Apache-2.0. Popularity signal: 8,855 stars. Score: 7.9/10

Production Readinessw: 15%

6.0

Battle-tested: 8,855 stars. Peer review: 25 contributors. Versioned: v0.8.0. Licensed: Apache-2.0. Age: 1.8 years. Maintenance: last commit 151d ago. Score: 6/10

Ecosystem Integrationw: 10%

8.1

Fork interest: 692. Major ecosystem: Python. Integration-friendly: Apache-2.0. Adoption: 8,855 stars. Has web presence. Score: 8.1/10