AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

AI Agents

AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.

Official site ↗1199 articles
In the glossary:AI agentAutonomous AgentAgentic WorkflowTool UseMulti-Agent System
Cursor Finds: 63% of Opus 4.8 Max's Benchmark Wins Are Search, Not Code
Research·Cursor Blog

Cursor Finds: 63% of Opus 4.8 Max's Benchmark Wins Are Search, Not Code

Jun 28, 2026·2 min
Vercel Teaches AI Agents to Understand Product Decisions, Not Just Copy Code
Creative

Vercel Teaches AI Agents to Understand Product Decisions, Not Just Copy Code

Jun 28, 2026·2 min
60% of Americans repelled by the word "AI" in brand advertising — WordPress VIP survey
Ethics

60% of Americans repelled by the word "AI" in brand advertising — WordPress VIP survey

Jun 28, 2026·3 min
Malaysia's Respond.io Raises $62.5 Million for AI Agents for Business Messaging
Autonomous

Malaysia's Respond.io Raises $62.5 Million for AI Agents for Business Messaging

Jun 28, 2026·2 min
Claude and AI agents are burning tokens faster than forecast — businesses are learning 'tokenomics'
Hardware·Wired

Claude and AI agents are burning tokens faster than forecast — businesses are learning 'tokenomics'

Jun 28, 2026·2 min
How to Design Tools for AI Agents: Working Practices and Common Mistakes
Creative

How to Design Tools for AI Agents: Working Practices and Common Mistakes

Jun 15, 2026·2 min
NewCore raises $66M to give AI agents corporate credentials
Autonomous

NewCore raises $66M to give AI agents corporate credentials

Jun 15, 2026·2 min
AI agents manage HR processes, but HRIS doesn't see who made the decision
Autonomous·Habr AI

AI agents manage HR processes, but HRIS doesn't see who made the decision

Agents screen candidates and approve time off, but the system records only the outcome — the decision-maker and audit trail vanish.

Jun 15, 2026·2 min
Top themes
01MCP-Agents in Corporate Systems: How SimpleOne and Ainergy Integrated AI into Business ProcessesJun 15, 2026·2 min02Nine AI agents, one API quota: how Rate Governor prevents cascading failuresJun 15, 2026·2 min03Z.ai releases GLM-5.2: real million tokens and two levels of deep thinkingJun 15, 2026·2 min04Moonshot AI Launches Kimi Work — Desktop Agent with Swarm of 300 Sub-AgentsJun 15, 2026·2 min05Siemens releases AI agent for TIA Portal that understands your project architectureJun 15, 2026·2 min
Visa and OpenAI Created an AI-Agent Shopping System: How It Works and Whether to Trust It
LLM·ZDNet AI

Visa and OpenAI Created an AI-Agent Shopping System: How It Works and Whether to Trust It

Visa and OpenAI launched a partnership: ChatGPT agents can now independently make purchases — with virtual tokens, spending limits, and user

Jun 15, 2026·2 min
01Code agents: subscription vs API — pricing breakdown for custom harnessesJun 15, 2026·2 min02AI Agents as Interns: Why Access Rights Need to Be Limited UpfrontJun 15, 2026·2 min03MCP Server for Obsidian: How to Connect Your Personal Knowledge Base to Any LLMJun 15, 2026·2 min
Anthropic on AI Agents in Cybersecurity: Capabilities and Pitfalls
LLM·Habr AI

Anthropic on AI Agents in Cybersecurity: Capabilities and Pitfalls

Anthropic published research on the application of AI agents in cybersecurity — developer Edgar Sipki analyzed the document and asked diffic

Jun 15, 2026·2 min
Claude Code Launched Agent Team Mode: A Team of AI Agents Instead of One
LLM·Habr AI

Claude Code Launched Agent Team Mode: A Team of AI Agents Instead of One

The experimental Agent Team mode in Claude Code launches multiple independent agents in parallel: each breaks down tasks from a shared list

Jun 15, 2026·2 min
An engineer dictated a diary to an AI agent for four months — and realized memory matters more than the model
LLM·Habr AI

An engineer dictated a diary to an AI agent for four months — and realized memory matters more than the model

A developer built a voice diary system using faster-whisper and Telegram, but the main discovery proved surprising: reliable memory is more important than language model power.

Jun 15, 2026·2 min
Why developers argue about AI-agent memory: technique or philosophy?
Autonomous·Habr AI

Why developers argue about AI-agent memory: technique or philosophy?

Jun 15, 2026·2 min
How an AI agent organized a photo archive of 36,000 images and emails from 2005 in one evening
Creative·Habr AI

How an AI agent organized a photo archive of 36,000 images and emails from 2005 in one evening

Jun 15, 2026·2 min
Coinbase for Agents: AI agents gain access to user trading portfolios
LLM·AI News

Coinbase for Agents: AI agents gain access to user trading portfolios

Jun 15, 2026·3 min
Box AI Built an Agent for Corporate Content on LangChain's Deep Agents
LLM·LangChain Blog

Box AI Built an Agent for Corporate Content on LangChain's Deep Agents

Jun 15, 2026·2 min
Replit Launches Shopify Integration and New SEO Agent
Autonomous·@Replit

Replit Launches Shopify Integration and New SEO Agent

Jun 11, 2026·2 min
From one-time commands to processes: GitHub added agents to Copilot CLI
LLM

From one-time commands to processes: GitHub added agents to Copilot CLI

Jun 11, 2026·2 min
Cursor Launches Design Mode: Edit UI with Clicks and Drawings, Agent Fixes Code
Creative

Cursor Launches Design Mode: Edit UI with Clicks and Drawings, Agent Fixes Code

Jun 11, 2026·3 min
AI Agents Restore Humanity in Global Healthcare
Medicine

AI Agents Restore Humanity in Global Healthcare

Jun 11, 2026·2 min
Google Launches Gemini 3.5 and Omni: Agents, Video Generation, and New Hardware
Medicine·Google AI Blog

Google Launches Gemini 3.5 and Omni: Agents, Video Generation, and New Hardware

Google announced its entry into the era of agentic AI models with Gemini 3.5 and Gemini Omni, capable of solving complex tasks and generatin

Jun 11, 2026·3 min
Replit Launches Parallel AI Agents to Speed Up Development
Autonomous·@Replit

Replit Launches Parallel AI Agents to Speed Up Development

Replit integrated parallel AI agents into its IDE. Multiple agents now work simultaneously on tasks, reducing development time by 3-4x.

Jun 11, 2026·2 min