#knowledge-graph Repositories
Discover 210 active open source GitHub repositories tagged with #knowledge-graph, accumulating 1,149,690 total stars (averaging 5,474 stars per project). Leading this topic is Graphify-Labs/graphify with 151,427 stars.
210 repositories total
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Chinese-English sensitive words, language detection, Chinese-foreign mobile/phone attribution/operator query, name gender inference, phone number extraction, ID card extraction, email extraction, Chinese-Japanese name library, Chinese abbreviation library, character decomposition dictionary, vocabulary sentiment values, stop words, reactionary words list, violence-terror words list, simplified-traditional conversion, English simulation of Chinese pronunciation, Wang Feng lyrics generator, occupation name library, synonym library, antonym library, negation word library, car brand library, car parts library, continuous English segmentation, various Chinese word vectors, complete company names, ancient poetry library, IT library, finance library, idiom library, place name library, historical figures library, poetry library, medical library, diet library, legal library, car library, animal library, Chinese chat corpus, Chinese rumor data, Baidu Chinese Q&A dataset, sentence similarity matching algorithm collection, bert resources, text generation & summarization tools, cocoNLP information extraction tool, domestic phone number regex matching, Tsinghua XLORE: Chinese-English cross-language encyclopedia knowledge graph, Tsinghua AI technology series reports, natural language generation, NLU too hard series, automatic couplet data & robot, username blacklist list, crime legal terms & classification model, WeChat public account corpus, cs224n deep learning natural language processing course, Chinese handwritten character recognition, Chinese natural language processing corpus/datasets, variable naming artifact, word segmentation corpus library + code, task-oriented dialogue English dataset, ASR speech dataset + deep learning based Chinese
Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.
A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: https://logseq.io/p/NX4mc_ggEV
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal knowledge management (PKM), and an open-source Notion alternative. Based on Karpathy's LLM Wiki pattern.
A distributed, fast open-source graph database featuring horizontal scalability and high availability
One shared memory for every coding agent on your team. Claude Code, Cursor and Codex get a map of your code and your team's past decisions, so they pick up where you left off.
A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).
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.
Knowledge graph for identifying and filling learning gaps across 10 primary and secondary school subjects: 4,068 knowledge points, 6,429 prerequisite relationships, and 16,419 questions. Cross-checked item by item against national curriculum standards to diagnose and pinpoint the prerequisite knowledge points that have genuinely not been mastered, and provide a path for remedial learning.
A self-hostable, multi-tenant knowledge agent platform: unified RAG, knowledge graphs, multi-agent systems, MCP/Skills, sandboxes, and permission management. Yuxi = Cloud Agents + Knowledge RAG, a self-hosted knowledge agent platform for RAG, knowledge graphs, and multi-agent workflows.
Persistent memory for Claude Code, Codex, and 6 other AI agents, stored as plain Markdown in your Obsidian vault. New: Crew, a shared logbook so Claude Code, Codex, Cursor, and Grok Bot know what each other has done. 48 commands: semantic search, self-rewriting notes, keyless research, and scheduled agents.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
RuVector provides high-performance, real-time decision-making and agent memory, self-learning AI, and a vector GNN database built in Rust.
A bio-inspired cognitive memory engine โ a new paradigm for Graph RAG.
Extrapolating knowledge graphs from unstructured text using GPT-3 ๐ต๏ธโโ๏ธ
Agricultural Knowledge Graph (AgriKG): Information Retrieval in the Agricultural Field, Named Entity Recognition, Relation Extraction, Intelligent Question Answering, Decision Support
Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions โ with one command.
The open-source context layer for AI agents and enterprise AI search. Permission-aware search and cited answers across 30+ sources, including Slack, Drive, Jira, GitHub and Microsoft 365, for people and agents through MCP, SDKs and built-in agents. Self-hosted or Cloud.
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents โ Text & Multimodal
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
A personal knowledge base that builds and maintains itself. Drop in sources โ Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
:books: To Be Professional Developer From Zero To Mastery, Interactive MindMap, RoadMap(Learning Path/Interview Questions), xCompass, Weekly for Developer, to Learn Everything in ITCS :dizzy: Programmer's technical vision, knowledge management and career planning, improving personal and team R&D efficiency
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
Frequently Asked Questions
What is the most popular #knowledge-graph repository on GitHub?
The top ranked open source #knowledge-graph project on GitHub is Graphify-Labs/graphify with 151,427 stars. Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Which programming languages are most used in #knowledge-graph repositories?
Among the top ranked #knowledge-graph projects on GitHub, the most common programming languages are Python, Rust, TypeScript, JavaScript.
How is the #knowledge-graph repository ranking calculated?
We track 210 active open source repositories tagged with #knowledge-graph (500+ stars), totaling 1,149,690 stars with an average of 5,474 stars per repository. Rankings update daily from the GitHub API.