Memgraph

If your #GraphRAG pipeline runs embeddings for a COUNT query… You’re doing it wrong. #Text2Cypher is what you need for direct, analytical questions. See how → memgraph.com/blog/text-to-c… #AIEngineering #Memgraph

Prompt engineering: Which instructions and examples should I give the model? Context engineering: Which external information shall the model's response be based on? Have a look 👉 memgraph.com/blog/prompt-en… #AIEngineering #LLMs #GraphTech #Nemgraph

A leading retail bank, Capitec Bank, used #Memgraph to surface the network patterns behind APP scams, then ran the pipeline daily at scale. Results? Runs 3.5M+ scores daily in ~2 hours. Full walkthrough 👉 memgraph.com/webinars/how-c… Key highlights 👉 memgraph.com/blog/graph-mac…

#Infrastructure decisions age. Memgraph moved from co-located hardware to #Hetzner for: ✓ lower costs ✓ faster CI ✓ more reproducible benchmarks ✓ less ops overhead Full story 👉 memgraph.com/blog/memgraph-… #Memgraph #DevOps #GraphDatabase

We built the Graph of public skills -> skillinsight.io From a non-technical standpoint, Agent Skills are the procedural memory you keep in your head on how to solve a particular problem, which can be very valuable, whether you are aware of that or not. You are constantly adapting and changing that procedural memory since the task is usually not fully deterministic, hence it cannot be a script. Parallel to that, skills have caused some controversy for being a security vulnerability and hallucinated LLM brain fog, but more on that in the future. 

Staying on the positive side of things and ignoring the negatives for now, agent skills could hold all the operational knowledge, allowing agents to operate semi-autonomously or autonomously to solve the particular operational problem. 

An example of that would be compiling a Memgraph Rust query module, which is not an easy task since you need the environment, the Memgraph query module API dependency, and knowledge of how to actually do it. Most advanced LLMs, like Codex or Opus, succeed at this after many tries and failures. This is why we build skills for compiling and deploying C++, Rust, and Python query modules that let LLMs practically single-shot the whole process. 

Back to the topic of the graph of skills, what is the actuall problem here? So if you have hundreds or thousands of skills in your organisation, the question is: how are you going to maintain them, how will they learn and evolve, and how will agents access them? If the tool's API changes, so should the skills, which causes a cascade of events across the files. Then the question becomes: how are those connected and correlated? 

This is what graphs as a structure are built for, and this is what we in Memgraph are trying to solve from different angles. The graph of skills will serve as our test bench for running the evolution, traceability, and access to the skills, while improving @memgraphdb as the graph database that serves as a real-time context engine for AI.

571M+ Amazon reviews isn’t a prompt. It’s a graph problem. Build the #KnowledgeGraph, then run Atomic #GraphRAG in #Memgraph. Key session highlights 👉 memgraph.com/blog/building-…

Your AI did not suddenly get worse. It aged. #Context rot is what happens when old facts never get removed and new facts keep stacking. The result is slow drift, subtle wrong answers, and longer prompts that still do not stabilize behavior. 👉 memgraph.com/blog/ai-contex… #GraphRAG

Here is what Memgraph’s production telemetry stack looks like: ✓ AWS for ingestion and batching ✓ S3 as the source of truth ✓ ClickHouse for fast analytics over semi-structured events ✓ Grafana for dashboards and alerts Full write-up 👉 memgraph.com/blog/memgraph-… #Grafana #AWS

GraphRAG often fails due to pipeline sprawl, not retrieval. Atomic GraphRAG: run the pipeline as a single Cypher query in the DB, with 10x less orchestration code. Explainer by @mbudiselicbuda 👉 memgraph.com/blog/atomic-gr… #GraphData #Memgraph

Need vector search that scales without doubling storage? In this blog, David Iveković breaks down how Memgraph avoids duplicate vector copies and improves memory efficiency. Full write-up 👉 memgraph.com/blog/single-st… #Memgraph #VectorSearch #VectorIndex #GraphData #GraphRAG #RAG

#AI doesn’t fail because models are weak. AI fails because meaning is missing. And the companies that turn their implicit knowledge into structured context will see their AI systems become a competitive advantage that compounds. @dtomicevic explains how 👉memgr.ph/real-ai-bottle…

LLM apps don’t fail because prompts are bad. They fail because context is missing. This beginner’s guide explains what #ContextEngineering actually is and how developers use it to ship reliable RAG and agent workflows. Have a look 👉 memgraph.com/blog/context-e… #GraphRAG #Memgraph

#Memgraph 3.8 is out 🎉 ✨ Parallel Runtime ✨ Concurrent Edge WRITES on Supernodes ✨ Atomic GraphRAG ✨ Single Store Vector Index Release highlights 👉 memgraph.com/blog/memgraph-… #GraphRAG #Cypher #VectorSearch

Tools without context is how MCP turns into a security problem. @dtomicevic breaks down in this article why that is so 👉 memgraph.com/blog/security-… #MCP #EnterpriseAI #GraphTech #Memgraph

Nothing like turning a massive codebase into something you can query. #Linux kernel into #Memgraph with Code-Graph, around 1M entities. Let's see how the @rustlang footprint evolve 🦀 github.com/vitali87/code-…

Learn all about Sampling + Elicitation j in the #Memgraph #MCP experimental server to power interactive Cypher optimization. Catch the article 👉 memgraph.com/blog/memgraph-… #GraphRAG

Full session👉 memgraph.com/webinars/turn-… Most enterprise knowledge is buried in unstructured documents like PDFs making it hard to use. Unstructured2Graph, part of the #Memgraph #AI Toolkit, helps extract and transform it into a connected #KnowledgeGraph for #GraphRAG pipelines.

Need better accuracy to run natural-language Q&A over multi-layered #GraphData? Skip the old "#LLM → #Cypher" chain. Go for an #MCP-based RAG app. Full walkthrough 👉 memgraph.com/webinars/lesso… Key highlights 👉 memgraph.com/blog/building-… #Memgraph

Build an entity graph from an unstructured document in #Memgraph Cloud using Unstructured2Graph. Step-by-step guide  👉 memgraph.com/blog/unstructu… #GraphDatabases #GraphRAG

Most #AI teams are drowning in custom integrations. That’s why Anthropic introduced the Model Context Protocol (#MCP). It is an open standard that finally lets AI apps, #LLMs, and external systems talk to each other cleanly. Full session 👉 youtube.com/watch?v=nmAVOT… #Memgraph