Sealbook / Open source / AI agents & LLM apps

OpenSPG/KAG

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

knowledge-graphlarge-language-modellogical-reasoningmulti-hop-question-answeringtrustfulness

GitHub ↗Website ↗

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 8 months ago.

Similar projects

	Repository	Stars	Language	License	Activity
1	HKUDS/LightRAG[EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation	★ 40.2k	Python	MIT	Active
2	tirth8205/code-review-graphLocal-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, wit	★ 32.2k	Python	MIT	Active
3	ScrapeGraphAI/Scrapegraph-aiPython scraper based on AI	★ 31.9k	Python	MIT	Active
4	morluto/reaReverse engineer anything with agents, from app behavior down to native binaries.	★ 319.5k	TypeScript	MIT	Active
5	mattpocock/skillsSkills for Real Engineers. Straight from my .agents directory.	★ 296k	Shell	MIT	Active
6	affaan-m/ECCThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Code	★ 283.1k	JavaScript	MIT	Active
7	NousResearch/hermes-agentThe agent that grows with you	★ 254.9k	Python	MIT	Active
8	deepseek-ai/deepseek-harnessDeepSeek Harness: Everything is a Plugin.	★ 253k	TypeScript	MIT	Active