KAG
by OpenSPG (organization)
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… (description from the project’s GitHub page)
Repository facts
- Stars
- 9,110
- Forks
- 723
- Open issues and pull requests
- 173
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- OpenSPG · Organization
- Created
- Sep 21, 2024
- Last push
- Jan 28, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 9,426: dylanhogg/llmgraph
Create knowledge graphs with LLMs
508 starsJupyter NotebookMITLast push Oct 11, 2025
Rank 6,090: zjunlp/Prompt4ReasoningPapers
[ACL 2023] Reasoning with Language Model Prompting: A Survey
1,009 starsMITLast push May 21, 2025
Rank 82: jingyaogong/minimind
🧠 Train a 64M-parameter LLM from scratch in just 2h!
63,931 starsPythonApache-2.0Last push Sep 22, 2026
Rank 239: ScrapeGraphAI/Scrapegraph-ai
Python scraper based on AI
31,902 starsPythonMITLast push Oct 6, 2026
Rank 709: The-Pocket/PocketFlow
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
11,257 starsPythonMITLast push Jul 26, 2026
Rank 1,082: open-compass/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, rea…
7,527 starsPythonApache-2.0Last push Oct 16, 2026