[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93863":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":13,"stars7d":13,"stars30d":13,"stars90d":13,"forks30d":13,"starsTrendScore":13,"compositeScore":14,"rankGlobal":9,"rankLanguage":9,"license":15,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":18,"hasPages":16,"topics":19,"createdAt":9,"pushedAt":9,"updatedAt":20,"readmeContent":21,"aiSummary":22,"trendingCount":13,"starSnapshotCount":13,"syncStatus":23,"lastSyncTime":24,"discoverSource":25},93863,"graph-engineering","codejunkie99\u002Fgraph-engineering","codejunkie99","Graph engineering for AI agents: the 9-stage knowledge-graph pipeline (translated from SEU's graduate course) + task-graph orchestration patterns, as a Claude skill with teaching mode and paste-ready workflows",null,168,19,105,0,43.9,"MIT License",false,"master",true,[],"2026-09-21 04:01:26","# Graph Engineering\n\n**The discipline of designing the structures AI agents work through — not the prompts.**\n\nIt has two halves:\n\n1. **Knowledge graphs** — what agents *remember*. Nodes are entities and facts, edges are\n   relationships with time and provenance. Ontology → extraction → fusion → serving.\n2. **Task graphs** — how agents *work*. Nodes are jobs, edges are execution dependencies.\n   Parallel fan-out, separate verifiers, the stop rule, the human gate.\n\nPrompt engineers steered the model's words. Loop engineers steered its iterations.\nGraph engineers steer its **topology**.\n\nThis repo turns Southeast University's graduate Knowledge Graph course\n([npubird\u002FKnowledgeGraphCourse](https:\u002F\u002Fgithub.com\u002Fnpubird\u002FKnowledgeGraphCourse), 4.4K★,\ntaught in Chinese since 2019) — plus the modern agent-orchestration research behind\ntask graphs — into things you can actually use today.\n\n## What's inside\n\n| Path | What it is |\n|---|---|\n| [`graph-engineering\u002F`](graph-engineering\u002F) | **The skill.** Hand it to your agent (Claude Code \u002F any skill-compatible harness) — it learns the full 9-stage knowledge-graph pipeline, the task-graph patterns, and a teaching mode that explains every stage with diagrams drawn from *your* domain. |\n| [`graph-engineering\u002Freferences\u002F`](graph-engineering\u002Freferences\u002F) | The distilled course: [curriculum map](graph-engineering\u002Freferences\u002Fcurriculum.md) (translated, with links to the original Chinese decks), [modeling](graph-engineering\u002Freferences\u002Fmodeling.md), [extraction](graph-engineering\u002Freferences\u002Fextraction.md), [fusion + GraphRAG](graph-engineering\u002Freferences\u002Ffusion-and-llm.md), [task graphs](graph-engineering\u002Freferences\u002Ftask-graphs.md). |\n| [`WORKFLOWS.md`](WORKFLOWS.md) | Nine paste-ready prompt blocks — a `\u002Fkg-tutor` that teaches you the whole course interactively, plus eight single-purpose tools (`\u002Fkg-scope` → `\u002Fkg-rag`) that chain into a full build. |\n| [`dist\u002Fgraph-engineering.skill`](dist\u002F) | The packaged skill file. |\n\n## Install (two commands)\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fcodejunkie99\u002Fgraph-engineering.git\ncp -r graph-engineering\u002Fgraph-engineering ~\u002F.claude\u002Fskills\u002F\n```\n\nThen ask your agent to *build* (\"build a knowledge graph from my docs\") or to *teach*\n(\"teach me graph engineering\") — teaching mode walks the pipeline stage by stage with\nworked examples and generated diagrams, using your own project as the running example.\n\n## The 9-stage pipeline\n\n```mermaid\nflowchart LR\n  A[1 scope] --> B[2 representation] --> C[3 ontology] --> D[4 entities]\n  D --> E[5 relations] --> F[6 events] --> G[7 quality gate]\n  G --> H[8 fusion] --> I[9 serve to LLMs]\n```\n\nModel the domain **before** extracting. Fuse **before** storing. Verify at every stage.\nA knowledge graph is a product with a schema, not a pile of triples.\n\n## The task-graph rules (the other half)\n\n- Delete **fake edges**: an arrow is real only when work flows through it.\n- The **diamond**: split → parallel workers → *separate* verifier contexts → one owned merge.\n- The **stop rule** (Google DeepMind × MIT, 180 configurations): teams win ~80% on work that\n  splits; every team configuration loses on sequential work. The shape of the work decides.\n- The **human gate**: your approval sits exactly where a mistake is expensive to undo.\n\nDetails: [references\u002Ftask-graphs.md](graph-engineering\u002Freferences\u002Ftask-graphs.md)\n\n## Credits\n\nThe knowledge-graph half is an independent English distillation of 东南大学《知识图谱》研究生课程\n(Southeast University's graduate Knowledge Graph course), Prof. Peng Wang —\n[npubird\u002FKnowledgeGraphCourse](https:\u002F\u002Fgithub.com\u002Fnpubird\u002FKnowledgeGraphCourse). All original\nlecture PDFs are in Chinese and remain in the original repo; none are redistributed here.\nTask-graph material draws on Google DeepMind × MIT's\n[\"Towards a Science of Scaling Agent Systems\"](https:\u002F\u002Fresearch.google\u002Fblog\u002Ftowards-a-science-of-scaling-agent-systems-when-and-why-agent-systems-work\u002F)\nand Anthropic's published multi-agent engineering work.\n\nMIT licensed. Built by [@Av1dlive](https:\u002F\u002Fx.com\u002FAv1dlive).\n","这是一个面向AI智能体的图工程实践框架，将知识图谱构建与任务图编排两大范式系统化落地。核心包含9阶段知识图谱流水线（从领域建模、实体关系抽取到融合与RAG服务）和任务图编排模式（支持并行执行、独立验证、人工闸门等）。项目以Claude技能形式提供教学模式与即用型工作流，支持交互式学习与领域适配的图结构设计。适用于需要提升AI代理记忆一致性、任务可追溯性与执行可靠性的知识密集型场景，如企业知识管理、AI原生应用开发与复杂流程自动化。",2,"2026-07-27 02:30:03","CREATED_QUERY"]