A Neo4j solutions engineer argues that enriched knowledge graphs with pre-computed graph metrics let AI agents detect financial crime faster and more precisely than agents given raw graph data, citing…
Pinecone published a 2026 guide naming Pinecone Nexus, Databricks Genie, Snowflake Cortex, Microsoft IQ, Palantir Foundry, and Glean as the best knowledge engine platforms, with the disclosure that Pi…
A working example project called GraphSAGE-GraphRAG demonstrates that structure-aware retrieval using a Neo4j knowledge graph and an offline-trained GraphSAGE GNN can solve multi-hop reasoning that fl…
Neo4j, a graph database company, explains that decision traces stored in a context graph provide a structured, queryable record of how AI agents reach decisions, capturing the reasons, tools, and poli…
A developer tutorial demonstrates extending local LLM data feeding by storing embeddings in a Neo4j graph database and combining similarity search with full-text search, using a local LLM and Python p…
Neo4j detailed a multi-agent integration that grounds Salesforce Agentforce responses in a Neo4j knowledge graph using Aura Agent over the Model Context Protocol (MCP), moving graph-specific computati…
A Neo4j semantic layer built with Neocarta cut Text2SQL token costs by up to 81% on a 278-table BigQuery Census ACS catalog and up to 54% on a 264-table Databricks catalog, according to a Neo4j soluti…
A review of Blake McCarn's Paperless Knowledge Graph finds that while it enables chat with scanned documents and includes evidence-backed retrieval with strict refusal modes, the project lacks public …
Neo4j's Director of Engineering demonstrates using the company's new Document Intelligence tool to convert unstructured PDFs, such as a history assignment on the Swedish-Danish war of 1657–1658, into …
Neo4j AI Research Engineer Michael Hunger argues that Andrej Karpathy's LLM-maintained wiki recipe, which gained viral attention and inspired Google Cloud's Open Knowledge Format (OKF) in June 2026, c…
Simon Willison's blog post proposes a new approach to AI agent memory, suggesting it should be treated as a portable file format called 'memoryfield' rather than a complex pipeline. The format consist…
A developer released Birdy-Edwards Wraith 2.0, an open-source, fully local Facebook OSINT and SOCMINT investigation tool that adds batch URL processing, a HOG+CNN hybrid face detection pipeline, AI-ge…
A developer benchmarked LatticeDB, an embedded property-graph database written in Zig, against SQLite for graph traversal and found the performance gap is real but concentrated in deep queries. The de…
Neo4j principal consultant Jesús Barrasa published the first chapter of a series building an enterprise knowledge layer, modeling AcmeBank's operating structure as a graph to answer accountability que…
Neo4j's Going Meta Season 3 recap highlights the growing industry consensus that AI agents require ontologies, as argued by Frank Coyle of UC Berkeley at the AI Engineer World's Fair. The season's epi…
A developer has published a walkthrough demonstrating how to use SynapCores as a unified backend for both LlamaIndex vector and property graph stores, eliminating the need for separate databases. The …
An engineer from Wexa AI benchmarked five graph database platforms, including CognoDB Cloud, on a 352,768-edge citation network under free-tier constraints. The harness measured ingest, traversal, loo…
A developer's comparison of AI memory tools Mem0, Zep, LangChain Memory, and Letta reveals that real memory requires conflict resolution, not just retrieval. Mem0 uses a two-stage LLM call to add, upd…
Neo4j published a startup guide for building graph applications on its Aura cloud database, recommending installation of the Neo4j CLI and agent skills first, then using the neo4j-getting-started-skil…
Neo4j's Sr. Manager of Technical Product Marketing explains GraphSAGE, an inductive graph embedding model that generates embeddings for new nodes without retraining, using a three-step process of samp…