Mastodawn

OpenAI acquired the claw but there are various alternatives and even some with semantic graph brains. MemU has semantic linking, multi-hop reasoning, a unified multi-modal memory. Not using a graph database though. Am sure vendors are figuring out how to catch this train, won't take long.
#GraphAI
https://memu.pro/memory-graph-agent

Memory for Proactive 24/7 Agents | MemU - Let AI Agents Work for You

Always-on memory for proactive AI agents. Predict user intentions, act proactively, work for you 24/7 — even while you sleep.

MemU

Orbifold Consulting Nov 13

Node and graph embeddings are a bit of a burden if you want to do simple experiments: PyG (aka Torch Geometric) comes with a steep learning curve. This NEExT package is a lot easier and supports NetworkX and iGraph, Wasserstein and more.
https://github.com/ashdehghan/NEExT
https://skolouri.github.io/wegl/
#GraphML #GraphAI

Dr. Thompson May 30, 2025

📉 Millions lost. Insight ignored.
Your AI model might be brilliant—but if it can't see the structure, it will fail. Discover why Graph Neural Networks are outperforming Transformers in domains where accuracy, cost, and explainability matter most.
📊 Dive into benchmarks, breakdowns & real-world fraud/failure cases.

🔗 https://medium.com/@rogt.x1997/the-ai-misstep-costing-millions-why-ignoring-graphs-might-be-your-next-failure-b7ec337156ef

#GraphAI #MachineLearning #AIModels #Fintech
https://medium.com/@rogt.x1997/the-ai-misstep-costing-millions-why-ignoring-graphs-might-be-your-next-failure-b7ec337156ef

The AI Misstep Costing Millions: Why Ignoring Graphs Might Be Your Next Failure…

What if your AI model misses fraud in a banking graph simply because it wasn’t built to see the edges? This isn’t hypothetical. It’s a failure that cost a fintech firm $2.6M due to an over-reliance…

Medium

gihyo.jp Dec 27, 2024

Fullstack Al Dev 2024 開催レポート
https://gihyo.jp/article/2024/12/fullstack-ai-dev-2024-report?utm_source=feed

#gihyo #技術評論社 #gihyo_jp #AI #GraphAI #Raycast

Fullstack Al Dev 2024 開催レポート | gihyo.jp

今回のイベントの主な目的は、GraphAIやRaycastなどのAIツールの可能性を探り、AIエージェント開発に関する知見を共有し、さらにエンジニアコミュニティの交流を促進することでした。このレポートでは、本コミュニティの共同Founderかつ当日司会を務めた筆者が、各セッションの内容や会場の模様を紹介します。

gihyo.jp

Ludovic Moncla Nov 9, 2022

📢 Offre de stage : Recherche et classification de sous-graphes dans un #gnn pour la reconnaissance d’entités nommées imbriquées
https://perso.liris.cnrs.fr/lmoncla/offers/Sujet-Stage-Master-FIL-LIRIS.pdf #graphAI