Agents
The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.
The agentic stack, tracked daily: MCP and A2A protocols, LangChain/LangGraph, Claude Code, OpenAI Agents SDK, agent frameworks, benchmarks and orchestration patterns.
Latest in Agents
30 stories
Building a serverless A2A gateway for agent discovery, routing, and access control
In this post, you will learn how to build a serverless A2A gateway on AWS that hosts multiple agents behind a single domain using path-based routing (/agents/{a…
Set AI credit session limits in Copilot CLI and SDK
You can now set AI credit session limits in Copilot CLI and the GitHub Copilot SDK to cap the amount an agent spends in a session. This is especially usefulR…
How Inscribe uses Amazon Bedrock to stop document fraud in seconds
In this post, you will learn how Inscribe developed an agentic AI system using Amazon Bedrock that reasons across documents the way an expert fraud analyst woul…
Structured memory filtering with metadata in AgentCore Memory
In this post, you will learn how metadata works across configuration, ingestion, and retrieval, explore enterprise use cases including multi-agent and multi-ten…
Get started with the Claude apps gateway for Google Cloud
Anthropic's agentic coding tool Claude Code has worked with Google Cloud for a while now. An individual developer could easily point CLAUDE_CODE_USE_VERTEX=1 at…
Browser tools for GitHub Copilot in VS Code are generally available
Browser tools for GitHub Copilot in VS Code are now generally available. Agents can now drive a real browser, navigate live web apps, and feed what they find ba…
Meta's non-invasive brain-to-text AI is closing the gap with surgical implants
Meta's FAIR AI team uses Brain2Qwerty v2 to translate brain activity into typed sentences, with no implants or surgery required. The system reads magnetic signa…
Claude Sonnet 5 continues Anthropic's pattern of hiding price increases behind unchanged token rates
Claude Sonnet 5 ranks fifth in the Artificial Analysis Intelligence Index with 53 points and even beats the pricier Opus 4.8 on some agent-based tasks. But the …
Hidden code in Claude Code secretly flagged Chinese users
Anthropic is removing a hidden monitoring feature from its programming tool, Claude Code, after it sparked outrage on social media. The article Hidden code in C…
Introducing Claude Sonnet 5 on AWS: Anthropic’s most capable Sonnet model
Today, we’re excited to announce the availability of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and Claude Platform on AWS. Clau…
Anthropic launches Claude Science, an AI workspace built specifically for researchers
Anthropic released Claude Science, an AI workbench for researchers. More than 60 preconfigured skills cover fields like genomics and computational chemistry, an…
Claude Sonnet 5 is generally available for GitHub Copilot
Claude Sonnet 5 is Anthropic’s latest Sonnet-class model, now available in GitHub Copilot. It brings strong coding performance to everyday development and…
Implementing resilience patterns with Amazon Bedrock and LLM gateway
In this post, you will learn five practical patterns for building resilient generative AI applications on AWS, progressing from native Amazon Bedrock features t…
Build generative UI for AI agents on Amazon Bedrock AgentCore with the AG-UI protocol
This post walks through how AG-UI integrates into the Fullstack AgentCore Solution Template (FAST) to build interactive agent frontends on Amazon Bedrock AgentC…
SkillOpt: Agent skills as trainable parameters
AI agents often fail because their instructions, or skills, are manually modified with no guarantee of improvement. Learn how SkillOpt turns skill editing into …
NVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science
Life sciences has entered an era of computational scale, and for more than a decade, NVIDIA has built the full GPU-accelerated computing stack — spanning hardwa…
Build agents even faster with Gemini Enterprise Agent Platform’s fully-managed, remote MCP server
A couple of months ago, we announced that over 50 Google-managed MCP servers are available. Today, we’ll dive into how to use the Gemini Enterprise Agent Platfo…
Bringing speed and strong cost performance to the market with Gemini Omni Flash and Nano Banana 2 Lite
Great creative happens when your tools move at the speed of your ideas. To help you create rich, reliable experiences while reducing regeneration time and costs…
Copilot Agent is now available in JetBrains AI Assistant
Today, JetBrains and GitHub are announcing a deeper integration between JetBrains AI Assistant and GitHub Copilot. Millions of developers already rely on the Gi…
Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning
Editor’s note: This post is part of Into the Omniverse, a series focused on how developers, 3D practitioners, and enterprises can transform their workflows usin…
DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows
Professional translation is often a team-based process: translators, reviewers, and project managers must coordinate terminology, legal force, and accountabilit…
Towards Generalizable and Evidential Nuclear Magnetic Resonance-Based Molecular Structure Elucidation via Large Language Model Agent
Nuclear Magnetic Resonance (NMR) spectroscopy is the gold standard for molecular structure elucidation, yet interpreting complex spectra for unknown molecules r…
Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data
Demand for personalized financial advising is growing, but consistent advisor expertise is difficult to obtain, scale, and encode in LLM systems. Simple persona…
Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering
While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous en…
SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate i…
Parametric Skills
Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually a…
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions. We treat them as persistent-state systems: …
MCP Server Architecture Patterns for LLM-Integrated Applications
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to exte…
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
AI agents can't remember past conversations. They must constantly reload or retrieve context, which grows less efficient as tasks get longer and more complex. M…
Build an agentic AI healthcare claims pipeline with Amazon Bedrock and AWS HealthLake
In this post, we show you how to build an automated claims processing pipeline using two key Amazon Bedrock capabilities: Amazon Bedrock Data Automation for int…