AI-агенты
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.
1Password launches Unified Access to protect logins, tokens, and secrets used by AI agents
1Password introduced Unified Access, a platform that helps companies find vulnerable credentials, grant access to AI agents on demand, and t
LangChain: Large companies are deploying AI agents into production faster than startups
LangChain's agent engineering report shows an unexpected shift: large companies are already deploying AI agents into production more often t
Sam Altman's World tests AgentKit to link AI agents to iris scans
World has begun limited beta testing of AgentKit, a system that links AI-agent actions to the owner's identity verified through an iris scan
Agentic SOC in 2026: how AI agents accelerate cyber defense and where autonomy becomes dangerous
AWS showed how to connect Amazon Bedrock AgentCore to Slack via CDK and Lambda
Habr AI explained how memory helps AI agents remember conversations without losing context
Russian businesses froze 90% of generative AI projects and failed to bring them to production
Tecno readies OpenClaw-based EllaClaw for smartphones to automate routine tasks
Tecno plans to integrate the OpenClaw framework into its Ella assistant so smartphones can schedule events, handle files and exchange data b
ServiceNow introduced EVA — a new framework for evaluating voice AI agents
ServiceNow released EVA — a system that evaluates voice AI agents not only by task success, but also by dialogue quality, from response brev
Cursor questioned public AI benchmarks for code with five charts
Cisco introduced DefenseClaw — an orchestration and blocking layer for securing AI agents
Diasoft automated API and event tests with AI and shifted QA's role toward business logic
Runity showed how it is building an enterprise RAG assistant for Confluence and GitLab
Warp tested on real DevOps tasks: handles routine, but makes you think less
A Habr author checked how Warp behaves in real DevOps scenarios: the terminal built a Flask service, configured the server and deployment wi
OpenClaw has moved beyond the hype: what businesses and DevOps teams can already put to work
OpenClaw has evolved from a toy for enthusiasts into the center of a new AI agent race: companies are building multi-agent pipelines, while