What Is Hermes Agent? Nous Research's Self-Improving Agent Explained
Hermes Agent is Nous Research's MIT-licensed agent that keeps memory, writes its own skills and searches old sessions. What it is and how to run it safely.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Hermes Agent is Nous Research's MIT-licensed agent that keeps memory, writes its own skills and searches old sessions. What it is and how to run it safely.
A USN announces fixed Ubuntu packages; OVAL, OSV and VEX feeds carry the same data for machines. How each works, and how to run, parse and trust them.
CSME and the AMD PSP are security processors that boot before your CPU. What they run, how OEMs ship their updates, and the version checks admins can run.
Run Nextcloud for files, calendar and contacts and Immich for photos on one encrypted Docker server, reached over WireGuard, with tested 3-2-1 backups.
DNS cache poisoning makes a resolver store a forged answer. How Kaminsky, fragmentation, SAD DNS and MaginotDNS worked, and the settings that stop them.
Java trusts a server when its TrustManager builds a PKIX path to a root in the JVM truststore, usually cacerts. How it works and how to change it safely.
Agents write search queries from their context, so names and emails leak. Redact before the call, search through your own proxy and log hashes, not text.
Autoinstall replaced preseed on Ubuntu Server 20.04. Write a YAML config, deliver it via cloud-init NoCloud, test in a VM, keep secrets out, pin versions.
From BEAST in 2011 to Raccoon in 2020, each TLS attack broke a legacy feature. TLS 1.3 removed most of them; the lessons for your servers still apply.
Weekly insights on software supply chain security, delivered to your inbox.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.