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.
How LangChain Protected Agents in LangSmith from Credential Leaks
LangChain added Auth Proxy to LangSmith Sandboxes — an access control system that hides API keys from agents and restricts their outbound co
Google Created AI Agent AlphaEvolve to Automate Algorithm Design
DeepMind introduced AlphaEvolve — an evolutionary AI agent based on Gemini that automatically designs and optimizes algorithms. Google is al
LangChain Moves from Token Streaming to Agent Streams
DeepMind Presented Co-Scientist — Multi-Agent AI for Accelerating Scientific Research
How Replit Agent Solves User Loss Problem with a Single Prompt
WorkOS Introduces auth.md — An Open Protocol for AI Agent Registration
CopilotKit Redefines Architecture for AI Agents in 2026
CopilotKit released a new stack for agentic AI developers: AG-UI protocol, AIMock testing platform, and Pathfinder server—a complete product
Gemma 4 as an Agent: How to Teach a Model to Call Tools Independently
Google's open-source Gemma 4 model has learned to independently call tools for search and computations — a new tutorial shows how to impleme