Agents that remember: introducing Agent Memory
Cloudflare Agent Memory is a managed service that gives AI agents persistent memory, allowing them to recall what matters, forget what doesn't, and get smart...
20 articles
Cloudflare Agent Memory is a managed service that gives AI agents persistent memory, allowing them to recall what matters, forget what doesn't, and get smart...
By migrating our request handling layer to a Rust-based architecture called FL2, Cloudflare has increased its performance lead to 60% of the world’s top netw...
We are launching Flagship, a native feature flag service built on Cloudflare’s global network to eliminate the latency of third-party providers. By using KV ...
If you hold cryptocurrency, there's a very simple golden rule that you should always follow. Never hand over your seed phrase.
Two weeks ago, Google’s Quantum AI group published a zero-knowledge proof of a quantum circuit so optimized, they concluded that first-generation quantum com...
Learn how to integrate threat intelligence into your existing security stack with Recorded Future. Explore four stages of cyber maturity, four key integratio...
As OpenAI and Anthropic advance frontier AI, SentinelOne delivers AI-native, machine-speed cyber defense at global scale.
US authorities jail two Americans for aiding North Korean laptop farm scams that infiltrated over 100 firms
Have you ever taken a look at your Microsoft 365 mailbox rules? If not, it might be worth a few minutes of your time.
We're building AI Gateway into a unified inference layer for AI, letting developers call models from 14+ providers. New features include Workers AI binding i...
We built a custom technology stack to run fast large language models on Cloudflare’s infrastructure. This post explores the engineering trade-offs and techni...
OpenAI’s new frontier model focused on cybersecurity comes following Anthropic’s launch of Claude Mythos Preview and Project Glasswing
The EU cybersecurity agency looks to become the third Top-Level Root CVE Numbering Authority, alongside CISA and MITRE
Security leaders know that reducing risk is not just about finding the right exposures, but helping the organization act on them before known issues turn int...
Cybersecurity researchers have revealed that 108 malicious Google Chrome extensions have been quietly stealing user credentials, hijacking Telegram sessions,...
Barracuda says 88% of brute-force attempts in Q1 were from the region
AI agents and coding assistants interact with AWS resources through the Model Context Protocol (MCP). Unlike traditional applications with deterministic code...