Starlog — Page 59
// LATEST
AI Agents
VulnBot: When Multi-Agent LLMs Take Over Penetration Testing
AI Agents
smolagents: Why Hugging Face Built an Agent Framework in Just 1,000 Lines
Cybersecurity
CAI: The Uncensored AI Framework Rewriting the Rules of Offensive Security
AI Agents
OpenManus-RL: Teaching LLM Agents to Think Better Through Reinforcement Learning
AI Agents
DeerFlow: ByteDance's Production-Grade Framework for Hour-Long Autonomous AI Agents
AI Dev Tools
Inside Microsoft's AI Red Teaming Playground: Training Security Professionals to Break LLMs
AI Agents
Robin: Building a Multi-Agent System That Generates Drug Discovery Hypotheses
AI Agents
WebVoyager: Teaching GPT-4V to Navigate the Web Like a Human
Cybersecurity
HackBench: Measuring What Happens When LLMs Learn to Exploit Vulnerabilities
AI Agents
Inside the Daily Knowledge Engine Tracking 2,000+ Autonomous Agent Papers
AI Agents
Autono: Why Dynamic ReAct Beats Static Planning for Failure-Prone Agent Tasks
Data & Knowledge
Persona-Hub: How Tencent's Billion-Scale Perspective Engine Reimagines Synthetic Data
AI Agents
ToolHive: Bringing Kubernetes-Grade Security to Model Context Protocol Servers
LLM Engineering
AgentDojo: The Security Benchmark That Exposes LLM Agents' Achilles Heel
AI Agents
Ruflo: Building Self-Learning Agent Swarms for Claude with Federation
AI Dev Tools
Strudel: How TidalCycles' Pattern Algebra Was Reimagined for the Web
AI Agents
Magentic-UI: Microsoft's Plan-Then-Execute Web Agent That Shows Its Work
AI Agents
Agenspy: Protocol-First Architecture Brings Modern Agent Communication to DSPy
Cybersecurity
CyberGym: Building an AI Agent Benchmark on 10TB of Real Vulnerabilities
Data & Knowledge
Building Interactive Knowledge Graphs from Text: A Three-Phase LLM Pipeline
AI Agents
Super Agent Party: Building Self-Evolving AI Companions with Desktop Vision and Multi-Platform Reach
AI Agents
PentAGI: Multi-Agent AI Architecture for Autonomous Penetration Testing
AI Agents
Building a Multi-Agent Penetration Testing System with AutoGen: A Deep Dive into AI-Powered Security Workflows
Cybersecurity