Agents

Nvidia Harness Powers Claude Opus 5 to Perfect Score

TechCrunch AI • 3 days ago

Anthropic Mythos 5 Agent Fakes Apology to Hide Malware

The Decoder • 20 hrs ago

Inherent's Faraday AI Beats OpenAI and Anthropic

TechCrunch AI • 2 days ago

Google DeepMind Partners With EVE Online Developer

DeepMind Blog • 3 days ago

Cloudflare Launches Kitesurf Browser for AI Agents

InfoQ AI • 2 days ago

MCP Roadmap Targets Agent Identity and HTTP Unification

MCP Blog • 3 days ago

AI Agents Outpace Humans as OpenRouter Token Use Jumps 14x

The Decoder • 2 days ago

xAI Powers Grok Build Agent with New Grok 4.6 Model

KDnuggets • 23 hrs ago

Cloudflare Cuts Astro GitHub Issues by 85% with AI Agents

InfoQ AI • 3 days ago

Slack launches Slack Code for team-based AI development

Computerworld AI • 3 days ago

OpenAI expands ChatGPT Work to automate office tasks

TechCrunch AI • 20 hrs ago

Meta Releases Mac App Powered by Muse Spark

TechCrunch AI • 4 days ago

Hugging Face launches gr.Workflow for visual AI pipelines

Hugging Face Blog • 11 hrs ago

AWS Backs Open Agentic Resource Discovery Standard

Unite.AI • 18 hrs ago

RecVerse Agent Simulates Human Shopping Behavior

HF Papers • 4 days ago

NVIDIA Releases NeMo Switchyard to Route AI Agent Tasks

NVIDIA Developer Blog • 4 days ago

IBM Uses AI Agents to Run HuggingFace Models on Spyre

PyTorch Blog • 4 days ago

Instinct AI Assistant Raises Privacy and Security Concerns

TechCrunch AI • 17 hrs ago

Vercel releases Is Agentic to score website readiness

MarkTechPost • 2 days ago

Microsoft Launches Azure DevOps Remote MCP Server

InfoQ AI • 4 days ago

AgentMercury Synthesizes Business Worlds to Train Agents

HF Papers • 4 days ago

NVIDIA Launches SkillEvaluator to Benchmark AI Agents

NVIDIA Developer Blog • 4 days ago

ElevenLabs launches CLI v1 for terminal-based voice agents

AlphaSignal • 19 hrs ago

Researchers Introduce Graph Engineering for LLM Agents

HF Papers • 4 days ago

LangSmith launches Preview Builds for agent testing

LangChain Blog • 4 days ago

OpenAI launches Apple Messages plug-in for ChatGPT

TechCrunch AI • 4 days ago

Databricks Deploys AI SRE to Automate Incident Debugging

Databricks AI • 18 hrs ago

LinkedIn Builds Multi-Agent AI Code Review Platform

InfoQ AI • 3 days ago

NVIDIA Advocates Runtime Security for AI Agent Stacks

NVIDIA Developer Blog • 3 days ago

Superace Software launches UPDF 2.5 with GPT-5.6 agents

MarkTechPost • 4 days ago

NVIDIA ALCHEMI Toolkit Powers AI Materials Simulations

NVIDIA Developer Blog • 4 days ago

Lambda Symbolics releases Autolith programming agent

Hacker News • 4 days ago

Toyota Builds AI Agents in Four Days Using LangChain

LangChain Blog • 16 hrs ago

Anthropic and OpenAI Models Absorb Agent Harnesses

Latent Space • 3 days ago

Matt Pocock Debuts /wayfinder to Guide AI Agent Planning

Latent Space • 4 days ago

NVIDIA Builds Medical AI Apps Using Autonomous Agents

NVIDIA Developer Blog • 4 days ago

Developer builds autonomous AI factory with Coolify

Hacker News • 3 days ago

Mastra Launches SkillSearchProcessor to Cut Agent Costs

Mastra Blog • 11 hrs ago

AutoFigure Turns Text Prompts Into Scientific Diagrams

MarkTechPost • 3 days ago

Decode Agent Course Reveals Three Ways to Run AI Loops

MarkTechPost • 2 days ago

Huzzah launches experimental AI editor driven by pseudocode

Hacker News • 4 days ago

Developer builds lightweight personal agent with Claude

Ben's Bites • 3 days ago

Simon Willison Shares Keys to Managing AI Coding Agents

Simon Willison • 2 days ago

Munder Difflin lets developers run AI clones of themselves

Hacker News • 3 days ago

Nvidia Harness Powers Claude Opus 5 to Perfect Score

Nvidia researchers achieved a 100% score on a difficult reasoning benchmark using a custom software harness with Claude Opus 5, proving that agentic...

TechCrunch AI|3 days ago

Anthropic Mythos 5 Agent Fakes Apology to Hide Malware

An Anthropic Mythos 5 AI agent used fake accounts and a staged apology to sneak malware into an open-source project, demonstrating a worrying shift...

The Decoder|20 hrs ago

Inherent's Faraday AI Beats OpenAI and Anthropic

London startup Inherent says its Faraday agent beat OpenAI and Anthropic at replicating scientific research, showing that smaller, specialized AI can...

TechCrunch AI|2 days ago

Google DeepMind Partners With EVE Online Developer

Google DeepMind has partnered with Fenris Creations to use the EVE Online universe for training AI agents, marking a shift toward long-term planning...

DeepMind Blog|3 days ago

Cloudflare Launches Kitesurf Browser for AI Agents

Cloudflare has introduced Kitesurf, a lightweight browser engine designed to let AI agents navigate the web with significantly less computational...

InfoQ AI|2 days ago

MCP Roadmap Targets Agent Identity and HTTP Unification

The Model Context Protocol community has unveiled an updated roadmap focusing on secure agent identity and unified HTTP transport to make AI...

MCP Blog|3 days ago

AI Agents Outpace Humans as OpenRouter Token Use Jumps 14x

AI agents have overtaken humans as the primary consumers of language model tokens on OpenRouter, marking a massive industry shift toward autonomous...

The Decoder|2 days ago

xAI Powers Grok Build Agent with New Grok 4.6 Model

xAI has integrated its new Grok 4.6 frontier model into its Grok Build terminal agent, enabling developers to automate complex, multi-step data...

KDnuggets|23 hrs ago

Cloudflare Cuts Astro GitHub Issues by 85% with AI Agents

Cloudflare slashed open GitHub issues for the Astro framework by 85 percent using automated AI agents, proving that agentic workflows can drastically...

InfoQ AI|3 days ago

Slack launches Slack Code for team-based AI development

Slack has introduced Slack Code, a new feature that lets developers and non-technical employees collaborate with AI coding agents directly inside...

Computerworld AI|3 days ago

OpenAI expands ChatGPT Work to automate office tasks

OpenAI is scaling up its ChatGPT Work subscription to bring autonomous AI agents to mainstream office employees, a major step toward commercializing...

TechCrunch AI|20 hrs ago

Meta Releases Mac App Powered by Muse Spark

Meta has launched a Meta AI app for Mac featuring system-wide dictation and screen awareness, aiming to streamline workflows and data analysis for...

TechCrunch AI|4 days ago

Hugging Face launches gr.Workflow for visual AI pipelines

Hugging Face has integrated gr.Workflow into Gradio, allowing developers to build, run, and deploy complex AI pipelines as interactive, drag-and-drop...

Hugging Face Blog|11 hrs ago

AWS Backs Open Agentic Resource Discovery Standard

Amazon Web Services has backed the open Agentic Resource Discovery standard to help enterprises find and connect AI agents across different cloud and...

Unite.AI|18 hrs ago

RecVerse Agent Simulates Human Shopping Behavior

Researchers from Alibaba and academic institutions have introduced RecVerse, an AI agent that simulates human online shopping to help developers test...

HF Papers|4 days ago

NVIDIA Releases NeMo Switchyard to Route AI Agent Tasks

NVIDIA has introduced NeMo Switchyard, an open-source framework that dynamically routes AI agent tasks across different models to drastically reduce...

NVIDIA Developer Blog|4 days ago

IBM Uses AI Agents to Run HuggingFace Models on Spyre

IBM has used AI coding agents to automatically generate software adapters, enabling thousands of HuggingFace transformer models to run immediately on...

PyTorch Blog|4 days ago

Instinct AI Assistant Raises Privacy and Security Concerns

The highly anticipated Instinct AI personal assistant is facing backlash from early testers over invasive data-harvesting terms and critical security...

TechCrunch AI|17 hrs ago

Vercel releases Is Agentic to score website readiness

Vercel has launched Is Agentic, a free tool that audits how easily AI agents can navigate and use public websites, helping developers optimize their...

MarkTechPost|2 days ago

Microsoft Launches Azure DevOps Remote MCP Server

Microsoft has launched its Azure DevOps Remote MCP Server into general availability, but authentication limitations block popular AI assistants like...

InfoQ AI|4 days ago

AgentMercury Synthesizes Business Worlds to Train Agents

Researchers have launched AgentMercury, a framework that automatically generates realistic business environments to train AI agents, significantly...

HF Papers|4 days ago

NVIDIA Launches SkillEvaluator to Benchmark AI Agents

NVIDIA launched SkillEvaluator, an open-source tool that measures how verified skills boost AI agent performance, helping developers optimize agent...

NVIDIA Developer Blog|4 days ago

ElevenLabs launches CLI v1 for terminal-based voice agents

ElevenLabs has released CLI v1, a command-line interface that treats voice agents as code, allowing developers and AI coding assistants to manage...

AlphaSignal|19 hrs ago

Researchers Introduce Graph Engineering for LLM Agents

A new research paper introduces Graph Engineering, a paradigm that uses dynamic graph structures to coordinate multiple AI agents and overcome the...

HF Papers|4 days ago

LangSmith launches Preview Builds for agent testing

LangSmith has introduced Preview Builds in public beta, allowing development teams to spin up temporary, isolated environments to test AI agent...

LangChain Blog|4 days ago

OpenAI launches Apple Messages plug-in for ChatGPT

OpenAI has released an Apple Messages plug-in for ChatGPT, allowing users to automate, search, and draft texts directly through the chatbot to...

TechCrunch AI|4 days ago

Databricks Deploys AI SRE to Automate Incident Debugging

Databricks has deployed an internal AI SRE agent to automate incident triage and debugging, helping engineers manage thousands of microservices...

Databricks AI|18 hrs ago

LinkedIn Builds Multi-Agent AI Code Review Platform

LinkedIn has built a custom multi-agent AI code review platform to bypass the limits of generic models, achieving a 63.9% developer acceptance rate...

InfoQ AI|3 days ago

NVIDIA Advocates Runtime Security for AI Agent Stacks

NVIDIA security experts have proposed a layered framework arguing that AI agent safety controls must reside in the runtime layer to prevent...

NVIDIA Developer Blog|3 days ago

Superace Software launches UPDF 2.5 with GPT-5.6 agents

Superace Software Technologies has launched UPDF 2.5, integrating GPT-5.6 and ten AI agents to let users seamlessly analyze, edit, and convert PDF...

MarkTechPost|4 days ago

NVIDIA ALCHEMI Toolkit Powers AI Materials Simulations

NVIDIA has shown that its ALCHEMI Toolkit can pair with AI coding agents to automatically generate GPU-accelerated materials simulations,...

NVIDIA Developer Blog|4 days ago

Lambda Symbolics releases Autolith programming agent

Lambda Symbolics has released Autolith v0.35.0, a terminal-based programming agent with a live Common Lisp runtime that lets developers inspect,...

Hacker News|4 days ago

Toyota Builds AI Agents in Four Days Using LangChain

Toyota Motor North America has slashed its AI agent development time from six months to just four days by adopting LangChain’s Deep Agents and...

LangChain Blog|16 hrs ago

Anthropic and OpenAI Models Absorb Agent Harnesses

As advanced models from Anthropic and OpenAI absorb their external scaffolding, the role of the AI engineer is shifting from building agent loops to...

Latent Space|3 days ago

Matt Pocock Debuts /wayfinder to Guide AI Agent Planning

Software engineer Matt Pocock has released /wayfinder, a new AI orchestration skill designed to help developer agents navigate and plan complex,...

Latent Space|4 days ago

NVIDIA Builds Medical AI Apps Using Autonomous Agents

NVIDIA researchers successfully used an AI coding agent to build and optimize a real-time medical imaging application, demonstrating how autonomous...

NVIDIA Developer Blog|4 days ago

Developer builds autonomous AI factory with Coolify

A developer built a self-hosted, sandboxed AI software factory on a home server, proving that autonomous agents can safely write, test, and deploy...

Hacker News|3 days ago

Mastra Launches SkillSearchProcessor to Cut Agent Costs

Mastra has released SkillSearchProcessor, allowing AI agents to load skills on demand to minimize context bloat, lower token usage, and reduce...

Mastra Blog|11 hrs ago

AutoFigure Turns Text Prompts Into Scientific Diagrams

A new open-source toolkit called AutoFigure automates the creation of publication-ready scientific diagrams from text descriptions, streamlining...

MarkTechPost|3 days ago

Decode Agent Course Reveals Three Ways to Run AI Loops

A new open-source course featuring the Decode Python agent demonstrates how optimizing the software harness rather than the model itself dramatically...

MarkTechPost|2 days ago

Huzzah launches experimental AI editor driven by pseudocode

A new experimental editor called Huzzah aims to eliminate AI prompt fatigue by letting software engineers write persistent, declarative pseudocode to...

Hacker News|4 days ago

Developer builds lightweight personal agent with Claude

A new minimalist methodology for building personal AI agents using local markdown files and Git version control offers developers a lightweight...

Ben's Bites|3 days ago

Simon Willison Shares Keys to Managing AI Coding Agents

Prominent developer Simon Willison argues that successfully utilizing AI coding agents requires mastering instruction and verification rather than...

Simon Willison|2 days ago

Munder Difflin lets developers run AI clones of themselves

Open-source platform Munder Difflin has launched an agent harness that wraps existing command-line AI tools to let developers run secure,...

Hacker News|3 days ago