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
Alibaba Launches AI Agents for Small Businesses to Automate Cross-Border Commerce
Creative·3DNews AI

Alibaba Launches AI Agents for Small Businesses to Automate Cross-Border Commerce

Apr 28, 2026·3 min
AWS explained how to convert a text-based AI agent into a voice assistant on Nova 2 Sonic
Creative

AWS explained how to convert a text-based AI agent into a voice assistant on Nova 2 Sonic

Apr 28, 2026·3 min
n0x Developer Taught His Browser Agent to Open Sites and Take Screenshots
LLM

n0x Developer Taught His Browser Agent to Open Sites and Take Screenshots

Apr 28, 2026·3 min
FIDO Alliance, Google, and Mastercard Create Standard for AI Agents in Online Shopping
Autonomous

FIDO Alliance, Google, and Mastercard Create Standard for AI Agents in Online Shopping

Apr 28, 2026·2 min
Amazon launches OpenAI products on AWS after review of Microsoft exclusive partnership
Autonomous·TechCrunch

Amazon launches OpenAI products on AWS after review of Microsoft exclusive partnership

Apr 28, 2026·2 min
Google Antigravity: How to Connect Rules, Skills, and Workflows for Reliable AI Agents
Autonomous

Google Antigravity: How to Connect Rules, Skills, and Workflows for Reliable AI Agents

Apr 28, 2026·2 min
AWS Shows How Amazon Nova Act Automates Competitor Price Monitoring
Autonomous

AWS Shows How Amazon Nova Act Automates Competitor Price Monitoring

Apr 28, 2026·2 min
Anthropic Accidentally Revealed Claude Code Source Code, Raising New Security Questions
LLM·Guardian

Anthropic Accidentally Revealed Claude Code Source Code, Raising New Security Questions

Anthropic mistakenly released a Claude Code update containing a link to an archive of nearly 2,000 internal files; the leak rapidly spread a

Apr 28, 2026·3 min
Top themes
01Anthropic and OpenClaude: why 'free' Claude Code in 2026 isn't really freeApr 28, 2026·3 min02Anthropic bets on Cowork: agent could surpass Claude Code in market sizeApr 28, 2026·2 min03Z.ai releases GLM-5V-Turbo — native multimodal model for visual programmingApr 28, 2026·3 min04NVIDIA at GTC 2026 Shifts Focus From Chips to Token Factories and Agent-as-a-ServiceApr 28, 2026·3 min05Habr: AI agents change delivery, and teams must rebuild the entire development cycleApr 28, 2026·3 min
Sova AI Released Android Assistant That Controls Phone Without PC and Root
LLM·Habr AI

Sova AI Released Android Assistant That Controls Phone Without PC and Root

Sova AI unveiled an Android application with an AI agent that opens apps, presses buttons, scrolls screens, and executes voice commands with

Apr 28, 2026·2 min
01Claude Sonnet and Jarvis Pattern: why AI agents might not need more than an operating systemApr 28, 2026·2 min02AI startup unveiled digital colleague for Zoom that reports to managersApr 28, 2026·2 min03Google Gemma 4, NVIDIA, and OpenClaw: Local AI Agents Without Per-Token BillingApr 28, 2026·3 min
Flant: How a Go Developer Turned Zed and Gemini into a Useful AI Agent
Medicine·Habr AI

Flant: How a Go Developer Turned Zed and Gemini into a Useful AI Agent

A Go developer from Flant described the path from slow IDE plugins to a combination of Zed, Gemini 3 Flash, and gopls-mcp, which provides an

Apr 28, 2026·3 min
MarkTechPost Demonstrates How to Build a Lightweight VLA Agent with Latent World Model and MPC
Autonomous·MarkTechPost

MarkTechPost Demonstrates How to Build a Lightweight VLA Agent with Latent World Model and MPC

In a new tutorial, MarkTechPost breaks down how to build a simplified embodied agent: it operates on RGB frames, learns a latent world model

Apr 28, 2026·2 min
Arcee AI Released Trinity Large Thinking — Open Reasoning Model for AI Agents
LLM·MarkTechPost

Arcee AI Released Trinity Large Thinking — Open Reasoning Model for AI Agents

Arcee AI open-sourced Trinity Large Thinking weights under Apache 2.0 license and focused on long agent scenarios, multi-step reasoning, and confident tool use.

Apr 28, 2026·2 min
Agentis Memory: Redis-Compatible Storage with Vector Search and Local Embeddings
Creative·Habr AI

Agentis Memory: Redis-Compatible Storage with Vector Search and Local Embeddings

Apr 28, 2026·3 min
Directum: Why Business Actively Discusses AI Agents but Hesitates to Deploy Them in Processes
Hardware·Habr AI

Directum: Why Business Actively Discusses AI Agents but Hesitates to Deploy Them in Processes

Apr 28, 2026·2 min
Agent Coding as Addiction: Why Developers Can't Stop
Medicine·Habr AI

Agent Coding as Addiction: Why Developers Can't Stop

Apr 28, 2026·3 min
PromptPilot: task scheduler for Claude Code and Codex that works while you sleep
LLM·Habr AI

PromptPilot: task scheduler for Claude Code and Codex that works while you sleep

Apr 28, 2026·2 min
Vulnerability in OpenClaw allowed silent privilege escalation to admin on exposed instances
Autonomous·Ars Technica

Vulnerability in OpenClaw allowed silent privilege escalation to admin on exposed instances

Apr 28, 2026·2 min
Google DeepMind Enables LLM to Rewrite Game Theory Algorithms and Surpass Experts
LLM

Google DeepMind Enables LLM to Rewrite Game Theory Algorithms and Surpass Experts

Apr 28, 2026·3 min
Luminarys AI Launches AI-Agent Platform with Skill Isolation and Cluster Deployment
Autonomous

Luminarys AI Launches AI-Agent Platform with Skill Isolation and Cluster Deployment

Apr 28, 2026·2 min
Z.AI showed how to build production-ready agentic systems on GLM-5 with tool calling
LLM

Z.AI showed how to build production-ready agentic systems on GLM-5 with tool calling

Apr 28, 2026·3 min
Habr AI: Why Agent Systems Need New Control and Safety Metrics
LLM·Habr AI

Habr AI: Why Agent Systems Need New Control and Safety Metrics

As organizations transition from chatbots to autonomous AI agents, they must evaluate not only response quality but also planning, tool call

Apr 28, 2026·3 min
Claude Code from Anthropic: How to Set Up an AI Assistant for Work Without Programming Skills
LLM·Habr AI

Claude Code from Anthropic: How to Set Up an AI Assistant for Work Without Programming Skills

A Claude Code guide shows how to transform Anthropic's tool from a developer assistant into a system for notes, knowledge bases, research, a

Apr 28, 2026·3 min