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.
OpenClaw turned out to be a costly autonomous agent: 81 million tokens and server conflicts
Firsthand experience installing OpenClaw showed that an autonomous AI agent can quickly run into infrastructure conflicts, consume tens of millions of tokens, and…
PAC1 exposed a weakness in reasoning models: a hardcoded agent passed the benchmark at lower cost
The closed PAC1 benchmark showed that in tasks involving files, JSON, and security traps, a fixed algorithm can sometimes work more reliably and at lower cost than…
project-graph-mcp helps AI agents see project architecture without extra tokens
The developers behind project-graph-mcp released an MCP server that builds a compressed code graph, shows dependencies, and helps AI agents understand a project…
Manus and AI agents are changing development: MVP code now appears in 20 minutes
Habr AI showed that reinforcement learning still trails classical optimization in logistics
KOMPAS-3D gets an AI agent that builds parts, drawings, and exports DXF on its own
Habr: according to Yandex Wordstat data, demand for "AI agents" trails bots and services
Piter Publishing released a book on GraphRAG and advanced RAG on knowledge graphs
Piter Publishing introduced a book on GraphRAG — an approach that combines knowledge graphs and vector search to make RAG systems more accurate and useful in…
OpenClaw has become a cultural phenomenon in China — mass events are already being dedicated to the agent
In China, OpenClaw has gone from an open-source AI agent to a mass phenomenon: it is installed via marketplaces, backed by subsidies, and the service has already…
Colleague Skill: how a Chinese project digitizes employees before dismissal
OpenClaw in China: why the buzz around the AI agent became a global market test
H Company introduces Holo3 — an AI agent for computer use with a record score on OSWorld-Verified
AWS showed how to restrict AgentCore AI agents' access to approved domains only
AWS added persistent session storage and shell command execution to Bedrock AgentCore
AWS showed how to preserve an agent's working directory between sessions in Bedrock AgentCore and run shell commands in the same microVM, so tests, builds, and git…
Raiffeisen Bank Is Building a Digital Twin of Its IT Landscape and Preparing Agentic RAG
Raiffeisen Bank explained how it is moving away from classic EA tools to its own platform, where the architecture repository becomes a digital twin of the IT…