#AI Agent
1073 related articles
5 MCP Servers That Unlock New Skills for Your AI Agents
Five practical MCP servers reviewed: Context 7 for up-to-date library docs, Playwright MCP for real browser control, AgentWire for converting 28 platforms into Markdown, Stripe's official MCP for payments, and CallForMe for phone calls.
DeepSeek Harness Penetration Mode in Practice: Automated SRC Vulnerability Discovery with AI Agents
A detailed guide to installing the DeepSeek Harness desktop client and configuring its penetration mode plugin, demonstrating an AI Agent automating port scanning, web enumeration, and vulnerability validation, plus practical notes on permission control and multi-Agent collaboration.
The Ultimate WorkBuddy Tutorial: AI Agents from Beginner to Real-World Practice
A nanny-level WorkBuddy tutorial for beginners: from core AI Agent concepts to installation and use, comparing onboarding difficulty, office compatibility, and cost with tools like Codex to help you own a digital employee at low cost.
Building Enterprise-Grade AI Agents from Scratch: A Three-Stage Learning Path from Bilibili's Comprehensive Tutorial
Analysis of Bilibili's 748-episode AI Agent beginner course: cognition section clarifies Agent vs. LLM differences, advanced covers LangChain, AutoGen, and multi-Agent collaboration, hands-on implements intelligent customer service and automated data analysis projects, with source code, courseware, and a learning roadmap.
Hermes Agent Self-Evolving Framework: A New Open-Source AI Agent Option
Based on a Bilibili creator's demo, this article analyzes the open-source AI Agent framework Hermes Agent's self-evolution mechanism, its differences from Open Cloud in Token consumption and long-term memory, and the real-world results of automatic skill generation.
Five Common AI Agent Proxy Mistakes: Making Your Agent Blend In
AI agent getting blocked? This article distills five proxy configuration mistakes: country-language mismatch, mid-flow IP rotation, datacenter IPs being detected, shared egress across tasks, and never checking the actual egress—plus fixes like sticky sessions, per-task routing, and logging route.reason.
Dedica: Can Your Website Pass AI Agents' 125 Tests?
Dedica is a new Product Hunt tool that uses 125 free checks to test whether websites work for AI Agents, with a fix for every issue that coding agents can act on.
The Essence of AI Agents: One Loop, Five Core Steps
What is the essence of an AI Agent? This article explains its core loop: send the conversation to the model, check for tool requests, execute tools, and update the conversation until an answer is reached. Learn the three components and max turn limits.
Six AI Agent Frameworks Compared: Choosing Wrong Costs Weeks—How to Choose Right in One Minute
A comparison of LangGraph, CrewAI, OpenAI Agents SDK, Claude Agent SDK, Google ADK, and Microsoft Agent Framework, with a one-minute selection guide.
AI Daily: GPT-6.1 Terra and Kimi K3.1 Pro Lead the Charge as Agent Security Alarms Sound
AI news in 24 hours: OpenAI releases GPT-6.1 Terra that can operate computers, Kimi K3.1 Pro tops open-source leaderboards with weights promised, MiniMax M3.1 Flash weights on Hugging Face, Cursor launches Agent SDK, while Anthropic and Qwen models face agent privilege-escalation security incidents.
AI Agents and MCP Internals: How LLMs Call Tools
A deep dive into how AI Agents and MCP work: how LLMs break free from text-only limits via tool calling, how the agent loop operates, how MCP connects tools and data with a unified standard, plus security risks and boundaries.
Why AI Agent-Recommended Leads Are Worth Following Up: The Four-Element Verification Method
How to verify AI Agent-recommended sales leads? This article introduces the four-element verification method: ICP match fields, dated buying signals, data source traceability, and CRM deduplication—intercepting unqualified leads through sampling audits before sales follow-up, making every recommendation traceable and reviewable.
Long-Running AI Agents Require Multi-Layer Feedback Loops
The LangChain Deep Agents course proposes a loop engineering framework that breaks AI agent feedback into execution, verification, and cross-run improvement loops to build reliable long-running agents.
Anthropic Builds Claude with Claude: The Engineering Philosophy of Separating the Brain from the Hands
Anthropic engineers Katelyn Lesse and Angela Jiang share how to build Claude with Claude, explaining the design principle of separating the "brain" from the "hands" in Opus 5.5, Claude Platform, and AI Agent engineering.
Asana AI Product Lead Shares AI Agent Best Practices
Asana's AI product lead shares AI Agent best practices, covering responsibility boundaries, human-in-the-loop design, data model anchoring, and evaluation iteration methods for product teams deploying Agents.
NVIDIA Open-Sources OpenShell: Putting a Safety Cage Around AI Agents
NVIDIA open-sources OpenShell, a runtime security sandbox for AI agents with kernel-level isolation and formal verification of policy changes to prevent permission runaway.
MuleSoft Agent Fabric Local Deployment and Testing in Practice
MuleSoft Agent Fabric supports local deployment and testing of AI Agents: with Docker and Anypoint Code Builder, you can run gateways, policies, and Broker locally with one click and test A2A without publishing to Exchange or deploying to the cloud.
MCP Protocol Explained: The N×M to N+M AI Integration Revolution
What is MCP (Model Context Protocol)? This article uses a USB-C analogy to explain MCP principles, breaking down the Host/Client/Server architecture, Tools/Resources/Prompts building blocks, stdio and SSE transports, plus comparisons with Function Calling and LangChain Tool, with a Python implementation and production best practices.
What Is MCP? The Open Standard That Connects AI to Every Tool
MCP (Model Context Protocol) is the open standard that lets AI apps connect to tools uniformly. This article explains MCP's Host, Server, and Client roles, the Tools, Resources, and Prompts building blocks, the full path of a tool call, plus two-way use in n8n and security risks.
MCP Explained: How AI Agents Connect t…
MCP Explained: How AI Agents Connect to Your Apps
Using an e-commerce support bot scenario, this visual guide explains how MCP solves the M×N AI-tool integration problem, why raw REST calls fall short, the Tools/Resources/Prompts primitives, and Host-Client-Server security.