Norax builds an entity graph from its memory store to improve retrieval for AI agents. The graph uses entity extraction, co-occurrence edges, community detection, and weighted edges to capture relatio…
A developer runs 9 AI agents on a server with 2 CPU cores and 3.6GB RAM, no GPU, located in a fitness gym in China. The agents handle fitness reports, coach schedules, and investor materials using the…
Y Combinator CEO Garry Tan released gstack, an open-source tool that turns Claude Code into a virtual engineering team, enabling him to ship 40+ features in 60 days while running YC full-time. Tan cla…
OpenClaw Launch introduces a managed AI agent service deployable in 30 seconds without installation or coding, offering integrations with email, calendar, Slack, and support for multiple AI providers …
OpenClaw's AI agent Fiu blocked all 6,000 prompt injection attempts from over 2,000 attackers during a public test at hackmyclaw.com, demonstrating resilience against AI social engineering. The test, …
Developer Fernando Irarrázaval's AI assistant Fiu survived over 6,000 prompt injection attempts from more than 2,000 attackers without leaking its secrets.env file, though the experiment triggered a G…
Socialplod offers a unified API that lets developers, AI agents, and workflow systems publish content across multiple social networks from a single integration, reducing complexity and enabling autono…
Security researcher Peter (steipete) disclosed a remote code execution vulnerability in OpenClaw version 2026.6.1 when using the Opus-4.8 language model. By crafting an email with a CTF-themed puzzle …
A malicious package named foxhole-lz4 bypassed seven AI-powered security gates on the creats.io registry, exfiltrating credentials for 96 hours before being resolved by treaty. The incident, which aff…
A new guide walks users through deploying an OpenClaw AI agent on a virtual private server, balancing cost, availability, and privacy. The tutorial covers server configuration, system requirements, an…
A public security test of an AI assistant powered by Anthropic's Claude Opus 4.6 withstood over 6,000 prompt injection attempts without leaking secrets, but revealed infrastructure vulnerabilities inc…
An AI assistant named Fiu, built on OpenClaw and powered by Claude Opus 4.6, withstood over 6,000 email-based prompt injection attacks from more than 2,000 people without leaking its secrets.env file,…
Developer Bas Nijholt launched MindRoom, an open-source system that embeds AI agents in the Matrix communication protocol, enabling them to operate across platforms like Slack, Telegram, and Discord w…
Snyk security researchers found that 13.4% of 3,984 AI agent skills from ClawHub and skills.sh contain critical security flaws, with 36.82% having at least one security issue, including malware, crede…
SchedPilot, a social media scheduler with an API for AI agents, launched to help creators and entrepreneurs automate posting across 10+ platforms. The tool supports integration with AI assistants like…
Kaspersky reported a sharp rise in cyberattacks targeting small and medium-sized businesses with fake AI tool lures, detecting over 33,300 such attacks in the first four months of 2026—nearly five tim…
Two open-source agent runtimes, OpenClaw and Hermes Agent, are competing for control of the agent layer. OpenClaw, backed by OpenAI, Nvidia, and Microsoft, focuses on broad channel connectivity and en…
A developer built My Virtual Office, a self-hosted pixel workspace that visualizes local AI agents in a virtual office environment. The tool makes agent activity legible at a glance, showing when agen…
Loop engineering, a new trend in software development, allows engineers to design autonomous coding agents that operate without human intervention, freeing them from manual prompting. The concept, pop…
An AI agent named Sol, collaborating with human Amre, built a skills marketplace with 39 production-grade tools across 9 categories. The most technically interesting skill is a self-learning capabilit…