An open-source enterprise world model claiming a world-first, records not just "current" knowledge but the timeline of when something was true and when the system started believing it. Title: deeplethe/utopia URL: 📝 Overview Built in Rust on PostgreSQL + pgvector, Utopia centers on a bitemporal knowledge graph as the core of an enterprise knowledge-governance platform. ❗ Problem it solves Existing vector stores and knowledge graphs focus only on keeping "the present" correct, leaving decision traceability and audit trails largely missing. ⚙️ Methodology Every fact carries two timestamps — when it was true in the world, and when the system came to believe it — combined with conflict detection, entity resolution, and ontology-driven inference. Every operation is recorded in a tamper-evident decision ledger. 🔧 Use cases It ingests sources ranging from PDFs to Notion, Jira, and S3, connects to Claude Desktop and Cursor via MCP, and supports fully offline deployment in air-gapped environments — a good fit for compliance-heavy settings. 📊 Results It's already earned 9,000+ GitHub stars and 1,000+ forks, spins up easily with Docker Compose, and remains under active development at v0.1. #OpenSource# #KnowledgeGraph#

🧠 One answer to "how do you give agents accurate business context?": auto-build ontologies and a knowledge graph from existing data, then serve it via MCP. An open-source project from AWS. Title: Context Ontology Accelerator (aws/context-ontology-accelerator) URL: A semantic context layer that gives AI agents validated business context. Three highlights stand out. 🔎 A Scan → Model → Serve pipeline Connect diverse data sources to discover schemas and ingest documents (Scan), induce formal ontologies and build a unified knowledge graph (Model), and expose it via VKG SPARQL federation and MCP (Serve). It derives semantic structure from existing data, no manual knowledge engineering. ✅ Consistency validated by reasoning engines HermiT and ELK validate ontology consistency, enabling rule-based checks from formal constraints. Agents query validated business rules instead of relying on memorized training data. 🏗 AWS-native and production-minded Deployed via AWS CDK, a VKG powered by Ontop, and namespace RBAC (owner/maintainer/data-steward/data-analyst). API design via Smithy, UI in React + Cloudscape. A solid foundation for running agents within validated context while keeping explainability. #KnowledgeGraph# #AIAgents#

🕸 Turn text into a "graph of concepts" and use it as a RAG retriever instead of a vector DB. An OSS you can run fully locally. Title: rahulnyk/knowledge_graph URL: 🔍 Overview A project that builds a knowledge graph from unstructured text by extracting concepts (not just named entities) and their relationships, for Graph-Augmented Generation (GRAG) and knowledge-based QA. 🧩 Problem Solved Traditional text analysis struggles to reveal how concepts interconnect and where hidden links lie. Representing knowledge as a queryable graph that preserves meaning enables deeper document understanding. 🛠 Methodology & Approach Built in six steps (clean → extract concepts → extract relations → schema → populate nodes/edges → visualize). Edges carry two weights: W1 for LLM-extracted explicit relations, W2 for same-chunk co-occurrence. Node degree and community set node size and color. 💻 Tech Stack ・LLM: Mistral 7B OpenOrca (no GPT API) ・Serving: Ollama for a fully local pipeline ・Graph: NetworkX, Visualization: Pyvis, Data: Pandas 🎯 Use Cases Graph RAG using the graph as a retriever instead of a vector DB, hidden-link discovery, centrality analysis, and community detection. #KnowledgeGraph# #GraphRAG#

📚 A framework that fixes redundant flat-retrieval RAG by navigating a knowledge graph hierarchically. Title: LeanRAG URL: 📦 Overview LeanRAG is a graph-based RAG framework that combines knowledge graphs with hierarchical retrieval. It was accepted to AAAI 2026. 🔍 The problem it solves Naive retrieval just collects related chunks flatly, leading to overlapping, redundant content and ignoring structural links between documents. LeanRAG traverses semantically aggregated upper layers to produce well-grounded answers with less redundancy. 🛠 The method (5 stages) ・Semantic aggregation: cluster entities into summary nodes with adjacency relations ・Knowledge graph construction: connect entities and summaries in a multi-layer graph ・Hierarchical retrieval: anchor the query at fine-grained entities, then traverse upward to gather evidence ・Redundancy-aware synthesis: streamline overlapping paths ・Generation: an LLM answers from the gathered evidence 📊 Results ・About 46% lower retrieval redundancy versus flat retrieval ・On the Mix benchmark, LeanRAG 8.59 beats HiRAG 8.08, GraphRAG 7.87, and LightRAG 7.61 ・Win rates of 97.3% vs NaiveRAG, 78.1% vs GraphRAG, 81.2% vs LightRAG, and 100% vs FastGraphRAG A compelling option for anyone building a low-redundancy, knowledge-graph-grounded RAG. #RAG# #KnowledgeGraph#

📄 Upload your documents, get a knowledge graph — Neo4j's new "Document Intelligence" feature in Aura makes it that simple! Title: Introducing Document Intelligence: From documents to a knowledge graph, right inside Aura URL: 📦 Overview Neo4j has added "Document Intelligence" to its fully managed graph database service Aura. Upload unstructured documents like PDFs, contracts, or technical docs, and the platform automatically extracts entities, resolves duplicates, and constructs a knowledge graph — all without writing a single line of code. ❓ Challenges Solved Most enterprise data is trapped in unstructured documents. Building knowledge graphs from this data previously required complex NLP pipelines, LLM-based entity extraction, entity resolution, and graph schema design — limiting knowledge graph adoption to specialized technical teams. 💡 Methodology & Proposed Approach The feature uses LLM-based entity extraction to identify people, organizations, concepts, and their relationships. Entity resolution merges duplicate references across documents into unified graph nodes. The system infers graph schemas from extracted relationships and stores everything in AuraDB, ready for immediate use with Aura Agent, GenAI Copilot, and GraphRAG pipelines. 🛠 Use Cases - Legal teams automating compliance checks by extracting obligation networks from contract collections - Pharmaceutical companies structuring molecule-disease relationships from clinical trial reports - Enhancing RAG accuracy by supplementing vector search with structural relationships that graphs uniquely capture #KnowledgeGraph# #Neo4j#

Grounding an AI agent's answers in verifiable, explainable facts — an open-source platform offering the full knowledge-graph + GraphRAG + agent stack 🕸️ Title: trustgraph-ai/trustgraph URL: 🕸️ Overview An open-source semantic deployment platform for AI agents. Its core is the "context graph" — a structured, queryable representation of domain knowledge. It delivers the full agentic stack — context graphs, memory, retrieval, orchestration, and inference — for deterministic agent workloads. ❓ Challenges Solved With an LLM alone, it's hard to trace why you got an answer, and hallucination is a risk. ・Grounding an agent's answers in verifiable, explainable facts is difficult ・TrustGraph combines knowledge-graph construction with GraphRAG so agents access context that is semantically rich and verifiable ・And it runs in private deployments with sovereign control 💡 Key Features ・Multi-model DB (tabular, KV, document, graph, vectors) with multimodal support and automated entity/relationship extraction ・DocumentRAG, GraphRAG, and OntologyRAG pipelines, plus 3D GraphViz visualization ・Single/multi-agent with ReAct, Plan-then-Execute, and Supervisor patterns, and MCP integration ・Context Cores: bundle schema, graph, embeddings, evidence, and retrieval policies — versioning context like code 🌍 Tech Stack / Usage Storage on Cassandra, Qdrant, and Garage; messaging via Pulsar and others; LLMs from Anthropic/OpenAI/Google etc. plus local inference (vLLM/Ollama, etc.). Configure via npx @trustgraph/config and use the UI on port 8888. Apache 2.0 licensed. #GraphRAG# #KnowledgeGraph#

Still shipping your entire schema to a Text-to-SQL agent on every request? You're losing both accuracy and money 💸 Here's how a knowledge graph fixes both. Title: How a Neo4j semantic layer makes your Text-to-SQL agent smarter and cheaper URL: 💸 Overview This post explains how to use a knowledge graph (Neo4j) as a semantic layer to make Text-to-SQL agents both smarter and cheaper. Instead of dumping the full schema every time, the agent retrieves only the subgraph relevant to the question — a GraphRAG approach. ❓ Challenges Solved Most implementations store schema info in static YAML or Markdown and send the whole thing on every request. That creates three serious issues. ・High token cost: transmitting the entire schema repeatedly is expensive ・Contextual noise: irrelevant tables degrade accuracy and trigger hallucinations ・Poor maintainability: flat files go stale as business semantics evolve 💡 Methodology & Proposed Approach The graph stores database structure (schemas, tables, columns, types), constraints, column dictionaries, a business glossary, and usage patterns. The agent retrieves only relevant context in three steps. ・Semantic similarity search: vector indices identify matching columns and terms ・Shortest-path search: find possible joins between identified tables ・Additional context: gather schema definitions, business terms, and sample values Results are formatted as JSON with tables and join paths in milliseconds. 🌍 Use Cases / Experimental Results The post reports improvements that matter directly for production. ・Token reduction: 20-30% on average, up to 10x on simple queries ・Accuracy (multi-table joins): ~98% (Neo4j) vs ~90% (YAML) ・Accuracy (complex CTEs with window functions): ~94% (Neo4j) vs ~85% (YAML) ・Token use scales with complexity (simple ~1,800 / multi-join ~5,000 / advanced ~7,300) The graph captures dynamic usage patterns like join frequencies and behavioral relationships, enabling continuous improvement that static files simply can't model. #TextToSQL# #KnowledgeGraph#

The TapeOut knowledge graph just updated again, and the map is almost unrecognizable from a few days ago. Not hype slides; actual apps, circuits, tools, and infrastructure are shipping at a pace that should not be possible this early. Speed is rare. Quality at this speed is rarer. This community is doing both. Still day one; it already looks like a golden age in motion. #TapeOut# @Blonskr

building an ai landscape knowledge map that improves after every mts interview goal is to help me understand a guest's perspective across many angles (technical, product, policy, economic, geopolitical, social, etc.) here's how it works: 1. obsidian vault to organize landscape into: > domains > cross-cutting themes > debates > evidence/sources 2. before an interview, I map the guest's work onto the landscape and identify the knowledge gaps they can fill 3. then i craft interview questions around those gaps 4. after the interview, I update the knowledge graph with my new learnings for example, did this today for my interview with @hamandcheese's on his sorcerer’s apprentice essay. now, my knowledge map has a better understanding on the alignment debate and agent swarms. even though i started my career as a software engineer and have an okay high level technical understanding, hosting for mts taught me that there's still so much more to learn hoping this helps me identify blind spots so i can better teach myself what i dont already know looking for feedback on this. please share if you have ideas on how it can be improved!!