Agents

Nvidia Harness Powers Claude Opus 5 to Perfect Score

TechCrunch AI • 1 day ago

Model Context Protocol Update Eliminates Sticky Sessions

AlphaSignal • 4 days ago

Cloudflare Launches Kitesurf Browser for AI Agents

InfoQ AI • 20 hrs ago

Cloudflare Debuts WriteGuard to Secure AI Agent Actions

InfoQ AI • 4 days ago

Inherent's Faraday AI Beats OpenAI and Anthropic

TechCrunch AI • 16 hrs ago

MCP Roadmap Targets Agent Identity and HTTP Unification

MCP Blog • 1 day ago

Cloudflare Cuts Astro GitHub Issues by 85% with AI Agents

InfoQ AI • 1 day ago

Natural Secures $100M Credit Line for AI Agent Payments

Unite.AI • 3 days ago

Google Brings Gemini Auto Browse to Android Chrome

Unite.AI • 4 days ago

Meta rolls out Pocket AI game-creation app in the US

TechCrunch AI • 2 days ago

NVIDIA Releases NeMo Switchyard to Route AI Agent Tasks

NVIDIA Developer Blog • 2 days ago

Waymo Integrates Google Gemini into Ojai Robotaxis

Unite.AI • 3 days ago

OpenAI launches Apple Messages plug-in for ChatGPT

TechCrunch AI • 2 days ago

NVIDIA Launches SkillEvaluator to Benchmark AI Agents

NVIDIA Developer Blog • 2 days ago

Harness Launches AI Agents to Automate Code Patching

Unite.AI • 3 days ago

LangChain adds AgentCore Payments middleware for AI agents

LangChain Blog • 4 days ago

Warp launches Warp Factories to automate software pipelines

TechCrunch AI • 4 days ago

LangSmith launches Preview Builds for agent testing

LangChain Blog • 2 days ago

Databricks launches single-prompt Genie Agent creation

Databricks AI • 3 days ago

Netflix Open-Sources Agentic Workflow for Causal Inference

InfoQ AI • 4 days ago

NVIDIA Advocates Runtime Security for AI Agent Stacks

NVIDIA Developer Blog • 1 day ago

LinkedIn Builds Multi-Agent AI Code Review Platform

InfoQ AI • 1 day ago

Anthropic and OpenAI Models Absorb Agent Harnesses

Latent Space • 1 day ago

Developer builds autonomous AI factory with Coolify

Hacker News • 1 day ago

Cloudflare Deploys AI to Enforce Engineering Standards

InfoQ AI • 1 day ago

Matt Pocock Debuts /wayfinder to Guide AI Agent Planning

Latent Space • 2 days ago

LangChain Launches Tuned Evaluators to Cut LLM Judge Costs

LangChain Blog • 3 days ago

AutoFigure Turns Text Prompts Into Scientific Diagrams

MarkTechPost • 1 day ago

SANY Ships SKT110Ei Autonomous Trucks to South America

Unite.AI • 3 days ago

NVIDIA Builds Medical AI Apps Using Autonomous Agents

NVIDIA Developer Blog • 2 days ago

Stanford wins Databricks Grounded Reasoning Cup

Databricks AI • 4 days ago

Developer builds lightweight personal agent with Claude

Ben's Bites • 1 day ago

Huzzah launches experimental AI editor driven by pseudocode

Hacker News • 2 days ago

Decode Agent Course Reveals Three Ways to Run AI Loops

MarkTechPost • 22 hrs ago

Munder Difflin lets developers run AI clones of themselves

Hacker News • 1 day ago

Hostinger automates cloud deployments with AI Connector

Unite.AI • 4 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|1 day ago

Model Context Protocol Update Eliminates Sticky Sessions

The Model Context Protocol has transitioned to a stateless architecture in its latest specification, eliminating complex session handshakes to...

AlphaSignal|4 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|20 hrs ago

Cloudflare Debuts WriteGuard to Secure AI Agent Actions

Cloudflare has launched WriteGuard in private beta, introducing fine-grained security controls to prevent AI agents from executing unauthorized write...

InfoQ AI|4 days 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|16 hrs 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|1 day 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|1 day ago

Natural Secures $100M Credit Line for AI Agent Payments

San Francisco startup Natural has secured a $100 million credit facility from Upper90 to fund credit and payment products for AI agents, establishing...

Unite.AI|3 days ago

Google Brings Gemini Auto Browse to Android Chrome

Google has launched Gemini in Chrome for all U.S. Android users, bringing its agentic auto browse task automation to mobile devices for the first...

Unite.AI|4 days ago

Meta rolls out Pocket AI game-creation app in the US

Meta has launched Pocket, an experimental AI-powered game creation app, to US users, signaling a major push to make vibe-coding and rapid software...

TechCrunch AI|2 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|2 days ago

Waymo Integrates Google Gemini into Ojai Robotaxis

Waymo has integrated Google Gemini as an in-car voice assistant inside its custom Ojai robotaxis, separating passenger-facing generative AI from...

Unite.AI|3 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|2 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|2 days ago

Harness Launches AI Agents to Automate Code Patching

Software delivery platform Harness has launched a suite of AI security agents designed to shrink the time it takes to find and patch software...

Unite.AI|3 days ago

LangChain adds AgentCore Payments middleware for AI agents

LangChain has introduced Amazon Bedrock AgentCore Payments middleware, allowing AI agents to securely pay for premium APIs and services using...

LangChain Blog|4 days ago

Warp launches Warp Factories to automate software pipelines

AI coding startup Warp has launched Warp Factories, an out-of-the-box infrastructure system that helps smaller companies deploy and manage autonomous...

TechCrunch AI|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|2 days ago

Databricks launches single-prompt Genie Agent creation

Databricks has updated its Genie Agents to allow users to build domain-specific AI assistants from a single prompt, simplifying how enterprises query...

Databricks AI|3 days ago

Netflix Open-Sources Agentic Workflow for Causal Inference

Netflix has open-sourced an AI agent workflow designed to automate observational causal inference, helping data scientists avoid common analytical...

InfoQ AI|4 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|1 day 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|1 day 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|1 day 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|1 day ago

Cloudflare Deploys AI to Enforce Engineering Standards

Cloudflare has turned its internal engineering standards into an active, AI-enforced control system, demonstrating how organizations can govern the...

InfoQ AI|1 day 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|2 days ago

LangChain Launches Tuned Evaluators to Cut LLM Judge Costs

LangChain has launched Tuned Evaluators for LangSmith to help developers automatically flag errors in production AI conversations at a fraction of...

LangChain Blog|3 days 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|1 day ago

SANY Ships SKT110Ei Autonomous Trucks to South America

SANY Group has shipped its first batch of SKT110Ei autonomous electric mining trucks to South America, marking a major international expansion for...

Unite.AI|3 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|2 days ago

Stanford wins Databricks Grounded Reasoning Cup

Stanford University won Databricks' inaugural Grounded Reasoning Cup, demonstrating that sophisticated system design is crucial for AI agents to...

Databricks AI|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|1 day 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|2 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|22 hrs 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|1 day ago

Hostinger automates cloud deployments with AI Connector

Hostinger is integrating infrastructure management directly into developer workflows through its Connector tool, helping programmers bypass...

Unite.AI|4 days ago