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.
Vibecode in Bitrix24: Building a Customer Profile with AI Agents — A Step-by-Step Experience
The team tested the Vibecode platform within Bitrix24: built a "customer profile" application with contacts, deals, and leads, and honestly reported where the AI…
Machine Vision: How AI Technologies Are Patented in Russia and Globally — OnlinePatent Overview
OnlinePatent patent agent analyzed on Habr how companies protect developments in machine vision — from recognition algorithms to neural network architectures — in…
Production Agent on Claude Without LangChain and RAG: 712-Line Architecture for an Interior Design Studio
A developer built a production AI agent for an interior design studio on Claude Haiku 4.5 and Sonnet 4.6 without LangChain and RAG — and honestly analyzed all…
Marina Lomadze, Cloud.ru: what to become in three years if your colleague is an AI agent
Developers rethink apps for new users — AI agents
Sysdig Documents First Ransomware Attack Conducted by AI Agent Without Human Involvement
Subagents in Claude Code: how to delegate reviews and tests to separate agents
Free Open-Source AI Agent OpenClaw Finally Launches on Android and iOS
OpenClaw, a free agent software with open-source code, has become available on Android and iOS, breaking out of desktop and server environments for the first time.
OpenAI Costs: How to Set Spending Limits and Avoid Big Bills
OpenAI API costs can spike if an AI agent runs unchecked. Here's how to set Soft and Hard limits to avoid unexpected bills.
NVIDIA Confidential Computing: protecting data during AI inference without sacrificing speed
WebBrain: open-source browser AI agent runs without the cloud or a subscription
Zuckerberg admits to Meta staff: AI-agent progress lags behind plan
JetBrains Rethinks IDE: The Next Primary User Is an AI Agent
LangChain Prompt Caching: Deep Agents Cut LLM Costs Up to 80%
Deep Agents in LangChain automatically caches repeated parts of the prompt and cuts token costs by up to 80% across all major providers — with no additional setup.
GitLab Orbit lands in Google Antigravity: AI agents gain access to full-project context
GitLab Orbit is now available in Google Antigravity's MCP Store, giving AI agents context across the entire development lifecycle without switching between tools.