These third-party projects greatly expand the ways agents and LLMs can draw on facts, documents, and conversations to deliver ...

Retrieval-augmented generation enhances the performance of AI agents by expanding their recall. It can do this in three ...

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

EverMind, a global AI company incubated by Shanda Group and dedicated to pioneering long-term memory infrastructure for the Agent era, today announced the official launch of Raven Agent — a deeply ...

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

Elastic open-sourced Atlas, a system built on Elasticsearch that maintains three categories of memory for agents. Atlas ...

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

AWS made the AgentCore harness generally available, turning agent plumbing into a managed service and the operational layer ...

Imagine chatting with an AI assistant that remembers your preferences, recalls past conversations, and adapts to your needs seamlessly. Sounds ideal, right? Yet, many of today’s AI systems fall short, ...

As Couchbase launches its AI Data Plane, the more interesting question is whether the NoSQL-era strengths it built for ...