Nvidia BlueField-4 STX adds a context memory layer to storage to close the agentic AI throughput gap

Nvidia's BlueField-4 STX reference architecture inserts a dedicated context memory layer between GPUs and traditional storage, claiming 5x token throughput and 4x energy efficiency for agentic AI ...

Google PM open-sources Always On Memory Agent, ditching vector databases for LLM-driven persistent memory

Enterprise AI teams are moving beyond single-turn assistants and into systems expected to remember preferences, preserve ...
IEEE

BridgeRouter: Automated Capability Upgrading of Out-Of-Bounds Write Vulnerabilities to Arbitrary Memory Write Primitives in the Linux Kernel

Abstract: Memory corruption vulnerabilities pose a significant threat to the Linux kernel, with out-of-bounds (OOB) vulnerabilities receiving particular attention due to their prevalence. The existing ...
GitHub

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.

When running the CLI tool, your agent help you code and do any task you can do on your computer. Below is a quick example of creating a stateful agent and sending it a message (requires a Letta API ...
IEEE

Protean: Adaptive Management of Shared-Memory in Datacenter Switches

Abstract: Datacenters rely on high-bandwidth networks that use inexpensive, shared-buffer switches. The combination of high bandwidth, bursty traffic patterns, and shallow buffers imply that switch ...
GitHub

Go bindings for zenoh-c: zero-copy, pub/sub, queryable protocol supporting router, peer, and client modes.

zenoh-go provides native Go bindings for zenoh-c, offering a clean and idiomatic Go API for the zenoh protocol. Here's why you should consider zenoh-go: zenoh-go/ ├── cmd/ # Example applications │ └── ...