Neo4j released AgentMemory for .NET, bringing graph-native short-term, long-term, and reasoning memory to Microsoft Agent Framework and Semantic Kernel developers, and published recordings from its Gr…
Neo4j explains that a context graph acts as a persistent memory system for AI agents, linking long-term enterprise knowledge, short-term conversation history, and reasoning memory to ensure consistent…
Semvec, a semantic memory system from Versino PsiOmega, achieves near-mem0 quality on the LOCOMO benchmark with zero generative-LLM calls at ingest, reducing context tokens by 87% and ingest time by ~…
Neo4j's starter repo powered the winning project at Hack the Video Agent Context Graph, a one-day hackathon hosted by HackerSquad at the AWS Builder Loft on Market Street, where 151 builders created 3…
AgentMemory for .NET, a native .NET implementation of Neo4j's graph-native agent memory model, has been released by independent developer José L. Latorre and verified 178 out of 178 against Neo4j's Te…
Neo4j's Enterprise Knowledge Layer proposes a shared, governed graph substrate to fix enterprise AI failures caused by scattered business context across agents, according to Jesús Barrasa. A benchmark…
An independent study by the UK's National Innovation Centre for Data (NICD) found that GraphRAG, a combination of vector and graph retrieval-augmented generation, makes AI agents 80% more truthful tha…
Public sector AI systems fail on high-consequence workforce questions because they lack a knowledge layer that connects fragmented data, according to Neo4j's Global Head of Public Sector & Workforce I…
Neo4j announced MCP for Aura, a hosted Model Context Protocol server included at no additional cost on Free, Professional, and Business Critical tiers of its Aura graph database service, with Virtual …
AI agents make decisions through a five-stage loop — understanding the goal, gathering context, deciding, acting, and learning — and failures typically begin when agents retrieve incomplete or disconn…
Enterprise AI fails not because of models or scaffolding but because agents lack the implicit business semantics that applications and humans supply themselves, according to Neo4j. The company propose…
Neo4j launched Virtual Graph, a zero-copy, zero-ETL solution that brings native graph intelligence to Databricks and Snowflake, enabling Cypher queries and graph algorithms directly on existing cloud …
Neo4j relaunched its GraphAcademy learning platform with an AI assistant called E.L.A.I.N.E. and a new MCP server for IDE integration. The platform offers free hands-on courses and labs for learning C…
Neo4j partnered with RocketRide, Butterbase, Daytona, Nebius, and Opsera at HackwithBay 3.0, where 200 builders used graph databases to build thoughtful agents for productivity. First-place team VeriG…
Neo4j's Aura Agent Hackathon drew 40 AI agent submissions from developers worldwide, with winners including a misinformation-mapping ConspiracyGraph Agent and a regulatory-risk graph agent, demonstrat…
Neo4j launched a redesigned GraphAcademy with a hands-on Neo4j Fundamentals course, editable data models, team learning features, an onboarding assistant, and public learner profiles. The update aims …
Neo4j argues that most enterprise AI projects fail due to data that lacks context, flexibility, and standardization, and introduces a knowledge layer to make data AI-ready. Gartner reports 63% of orga…
Neo4j Chief Scientist proposes that AI agents require three types of structured memory—long-term, short-term, and reasoning memory—organized as context graphs to ensure reliability and accuracy in aut…
Neo4j has been named a 'One to Watch' in Snowflake's 2026 Modern Marketing Data Stack Report for its graph database and analytics integration with Snowflake's AI Data Cloud, enabling advanced graph-dr…
Neo4j launched the Agent Memory Service (NAMS), a managed cloud service providing persistent, structured memory for LLM agents using a graph database with native vector indexes. The service offers sho…