#AI agents research
2447 related articles
·3 min
AI-Powered Vulnerability Discovery in Practice: A Complete Guide to LLM Security Applications
A deep dive into LLM applications in cybersecurity offense and defense, covering AI code auditing, automated vulnerability discovery, CTF Agents, and more, with tool selection guides and compliance guidelines.
Read more →
·5 min
The $60 Billion Cursor Acquisition: Birth and Deep Dive into the AI Programming Operating System
SpaceX acquires Cursor for $60B. How did this AI coding tool evolve from a VS Code fork into a software development operating system? Deep analysis of Agent orchestration, Origin hosting, and model strategy.
Read more →
·4 min
Five Stages of Agent Evolution: From Model Calls to DeepAgents — A Deep Dive
A detailed breakdown of five evolutionary stages of AI agent development, from simple API calls to DeepAgents multi-agent architecture, helping developers understand the full progression and make informed choices.
Read more →
·4 min
Hands-On with Claude Opus 5: The New AI Flagship That Crushes Competitors on Cost-Efficiency
A $400 hands-on test of Anthropic's flagship Claude Opus 5: from 3D game generation to physics simulations, benchmarked for cost-efficiency. Not the strongest, but the best value with 30% lower costs.
Read more →
·3 min
Gemma Surpasses 1 Billion Downloads: The Hidden Truth Behind Local LLM Adoption
Google's Gemma hits 1B downloads, but that's not 1B users. We break down the real drivers — embedded deployment, CI/CD pulls — and what Awesome Gemma means for the open-source AI ecosystem.
Read more →
·4 min
Four Stages of LLM Commercialization: The Evolution from Foundation Models to AI Agents
Explore the four stages of LLM commercialization: foundation models, prompt engineering, RAG, and AI Agents. Learn each stage's strengths, limitations, and a 3-month learning roadmap.
Read more →
·4 min
How Theo Rewrote His AGENTS.md to Double AI Coding Efficiency
T3 founder Theo shares how rewriting AGENTS.md and Skills configs doubled his AI coding output, covering trigger design, contrastive examples, and behavioral auditing.
Read more →
·4 min
Argentic: Building Toll Booths for AI Crawlers with the Lightning Network
Argentic uses the L402 protocol and Bitcoin Lightning Network to build a micropayment toll system for AI crawlers. This article analyzes its technical principles and implications for the agent economy.
Read more →
·3 min
The Five-Step AI Coding Method: Mastering Agents Like an Engineer
Matt Pocock's AI coding methodology: a five-step delivery system (Interrogate, Spec, Tickets, Implement, Review) with context management techniques to master any AI coding agent.
Read more →
·4 min
Qwen3 27B + DeepSeek Harness Real-World Testing: Local Open-Source Agent Performance Evaluation
Real-world testing of Qwen3 27B with DeepSeek Harness agent framework: deployment setup, visual understanding, reasoning intensity comparison, and token consumption data across multimodal tasks.
Read more →
·3 min
Codex vs Claude Code Real-World Comparison: Efficiency and Quality Differences When Building Apps from the Same Prompt
Real-world test comparing Codex and Claude Code building a Typeform alternative from the same prompt, revealing major differences in quality, efficiency, and cost.
Read more →
·3 min
What Is AGENTS.md: Can a Unified Configuration Standard for AI Coding Tools End Fragmentation?
AGENTS.md aims to provide a unified project configuration standard for AI coding tools like GitHub Copilot, Cursor, and Claude Code, addressing the proliferation of .cursorrules and CLAUDE.md files.
Read more →
·3 min
Cursor Turning from IDE into a Chatbot? Why Developers Miss the Old Experience
Cursor is shifting from an AI-enhanced code editor toward conversational Agent mode, sparking developer backlash. We analyze why more powerful AI may sacrifice the IDE experience developers loved.
Read more →
·2 min
GLM 5.3 Released: Frontier Coding Capabilities and Emergent Cybersecurity Abilities Explained
Zhipu AI releases GLM 5.3 with frontier coding capabilities and emergent cybersecurity abilities. This analysis covers technical breakthroughs in code generation, security auditing, and implications for developers.
Read more →
·3 min
Getting Started with Codex and Claude Code: A Beginner's Guide to AI Coding Agents
A detailed guide to Codex and Claude Code AI coding agents: core differences, target users, and beginner learning paths. From concepts to environment setup for zero-experience users.
Read more →
·3 min
GitHub Daily · August 22: The Rise of Agent Meta-Frameworks and Local-First AI Workbenches
GitHub Trending Aug 22: Agent meta-framework ruflo leads with 68K+ stars, Apache Maka pioneers local-first Agent governance, signaling AI's shift to orchestration and observability.
Read more →
·2 min
T3 Code: Orchestrating Multiple AI Coding Agents to Work as a Team
T3 Code is an open-source AI coding workbench that orchestrates multiple Agents like Codex and Claude Code to collaborate on the same project with defined roles for development and code review.
Read more →
·4 min
OpenAI Astra Approaching Release, Qwen Local Model Closing in on Closed-Source Frontier
OpenAI's next-gen model Astra nears release as multi-agent orchestrator; Qwen 3.8 27B local model surpasses multiple closed-source models on Agentic Index; Cursor launches Origin to challenge GitHub.
Read more →
·3 min
What Are Agent Skills? A Comprehensive Guide to the AI Agent Development Architecture Paradigm
Deep dive into Agent Skills architecture for AI agents, covering Skill framework definitions, MCP protocol, multi-agent collaboration, and practical applications for building enterprise-grade Agent systems.
Read more →
·3 min
Stripe Acquires OpenRouter: The Business Logic Behind Paying $7 Billion for an AI Model Gateway
Stripe acquires AI model aggregation platform OpenRouter for over $7B, targeting payment and routing data behind model calls. Analysis of the deal's strategy, Anthropic's revenue surge, and post-Transformer architectures.
Read more →