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.
Anthropic and ETH Zurich: a long CLAUDE.md worsens agent performance and raises costs
A study by ETH Zurich across 138 repositories found that long CLAUDE.md and AGENTS.md files often reduce coding-agent success rates while also increasing token…
Anthropic, OpenAI, and Cursor: Eight Levels of Agent Engineering Maturity
Habr AI broke down eight levels of agent engineering — from tab-complete and context engineering to background agents and autonomous teams that are already changing…
LangChain released Deep Agents for multi-step AI agents with memory and isolation
LangChain released Deep Agents, a library for AI agents that need planning, long-term memory, file context, and subagent isolation in long-running tasks.
Nvidia turned OpenClaw into an enterprise platform with security and local AI models
Nvidia introduced Agent Toolkit and NemoClaw for rapid and secure AI agent deployment
nullClaw on Zig outperformed OpenClaw in memory and startup in local AI agent tests
Tailscale acquired Border0 to protect enterprise networks from the influx of AI agents
Yandex at AI Dev Day Showed How AI Is Already Changing Development at Avito, Ozon, and T-Bank
At AI Dev Day, companies Yandex, Avito, Ozon, T-Bank, and Sber demonstrated where AI is already accelerating development and where the effect is still limited by…
Microsoft merges enterprise and consumer Copilot teams for a unified platform
Microsoft is merging its consumer and enterprise Copilot teams to ship features faster, reduce product fragmentation, and make the AI assistant a single experience…
OpenAI Released GPT-5.4 Mini and Nano — Near-Flagship Quality at Lower Cost
AWS selected 12 European AI startups and warned of the risk of an innovation drain from the region
Jensen Huang of Nvidia called OpenClaw the 'next ChatGPT' for the era of AI agents
Anthropic explained how to build skills for Claude Code and why teams need their own marketplace
NVIDIA released Agent Toolkit for secure deployment of enterprise AI agents
At GTC 2026, NVIDIA introduced the open source Agent Toolkit stack with OpenShell and AI-Q so companies can run AI agents with access, privacy, and cost controls.
Habr AI: how expensive LLMs became state managers and reduced development costs
Habr AI described a setup in which an expensive LLM stops writing code and becomes the state manager, while a low-cost worker takes over routine tasks and fixes.