While AI holds the promise of radically transforming KM, human oversight takes on intensified responsibilities for ensuring the knowledge provided is accurate, timely, and relevant as well as guarding ...

NUS researchers' MRAgent framework reduces LLM agent memory retrieval to 118K tokens per query — vs. 3.26M for LangMem — ...

Part of the SD Times 100 2026 series. See the full SD Times 100 2026 list for every category and honoree. Every conversation ...

Context graphs, graph memory, and ontologies for AI are converging. What does this mean for enterprise AI in 2026?

Couchbase AI Data Plane combines persistent agent memory, vector search and an enterprise MCP server that runs on-device when ...

The research project promises more efficient long-term recall by organizing knowledge around abstractions and cue-based ...

Sales, a function that obviously runs on language, has been among the least changed by the technology built on language.

One of the greatest weaknesses of AI agents that read and understand vast amounts of enterprise data is "hallucination"—the generation of plausible-sounding but factually incorrect information. KAIST ...

Google Cloud Summit came to London last week, and we took the opportunity to sit down with database execs Sailesh ...

Version 5.0 Modernizes DNN Engine, Adds LLM/VLM Support, and Enhances Core, Hardware Acceleration, and 3D Stack.

When major artificial intelligence platforms abruptly retire popular models or alter user access terms, developers and ...

Secure your AI agents against future quantum threats. Learn how to implement quantum-resistant cryptography within Model Context Protocol (MCP) environments.