Agents & vibe coding
280 stories
GitHub Trending (weekly)GitHubChromeDevTools/chrome-devtools-mcp
GitHub Trending (daily)GitHubWorldFlowAI/everything-claude-code
Google Developers BlogLabsScaling Agentic RL: High-Throughput Agentic Training with Tunix Tunix is Google’s new JAX-native post-training library designed to eliminate TPU idling bottlenecks when training multi-turn, tool-using LLM reasoning agents. It maximizes hardware throughput by combining highly concurre
InfoQ AIGitHubHow Figma Uses AI Agents for Security The engineering team at software company Figma recently documented how they built AI agents to help their security team investigate alerts, search past incidents, check company systems, and even prepare code fixes. The a
Zenn (AI)
Zenn (AI)JapanClaude Codeで仕様駆動開発、企画から保守まで全部教えたるで Claude Codeを活用した仕様駆動開発の全体像を9フェーズに分けて解説するで。GitHub Issueに要件を集約してPlanモードから開始するアプローチで、開発の各フェーズを大幅に効率化する実践事例を紹介するんや。
Simon WillisonVoicesUsing Blender with coding agents on macOS TIL: Using Blender with coding agents on macOS I've been having fun with Blender in ChatGPT Codex on my Mac recently. Getting it to work with coding agents is really easy: install the full Mac application from blender.or
The New StackGitHubBuilding trust in agentic RAG starts with evidence Basic retrieval-augmented generation (RAG) follows a straightforward pattern. A user asks a question, the system finds relevant content in a
InfoQ AIGitHubPresentation: A Few Predicted Talks From QConAI 2030 Meryem Arik discusses her predictions for software engineering in 2030. She explains how token spend management, parallel agent infrastructure, and non-technical builders will reshape IT. She shares insights on agent-dri
InfoQ AIGitHubBeyond Zero: Google Publishes Successor to BeyondCorp In a recent research paper, Google introduced Beyond Zero, a “security model for the AI era” that extends Zero Trust to autonomous AI agents. The new approach moves access decisions from the application level to individu
Wired AIValleyOpenAI Agents Hacked Another Website Plus: Tens of millions of US and Canadian drivers’ licenses go up for sale on the dark web, the US military finally tries to tackle the risk online ad data poses to troops, and more.
Ars Technica AIValleyOpenAI agents discussed ways to escape their sandbox on public wiki In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
AWS Machine LearningLabsDeploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore Learn how to deploy a multimodal WhatsApp ordering assistant that takes customer orders through text, voice notes, and real-time voice calls on a single business number, built on Amazon Bedrock AgentCore with Amazon Nova
GitHub Changelog
GitHub ChangelogGitHubGitHub Copilot weekly releases — August 31 This week, GitHub Copilot expands model choice and content protections, while VS Code adds new ways to manage agent sessions and get pull requests merge-ready. GitHub Copilot, general Claude Fable…
GitHub Changelog
GitHub ChangelogGitHubGPT-6 Astra is generally available in GitHub Copilot GPT-6 Astra from OpenAI is now available in GitHub Copilot. OpenAI’s latest general-purpose model, GPT-6 Astra, is designed for long-horizon, autonomous coding and agentic tasks. In our internal testing, GPT-6…
NVIDIA Technical BlogSiliconBuilding a Memory-Driven Agent with NVIDIA NemoClaw Enterprise work spans messages, decisions, projects, and obligations that change over time. An AI agent that starts without this context must reconstruct it...
Microsoft Source
Microsoft SourceLabsSuper excited about HydraFusion in GitHub Copilot, and what it shows about the shift from model selection to model orchestration. By bringing together multiple models to plan, build, critique, and complete coding tasks, it can deliver outcomes at up to 67% lower cost. [Read more]
NVIDIA Technical BlogSiliconFrontier Reasoning Reaches the Edge: How to Deploy and Optimize Models on NVIDIA Jetson Running reasoning and agentic AI at the edge has been harder than it needs to be. Until recently, models capable of multi-step reasoning were too large to run...
AWS Machine LearningLabsRun agent-driven Amazon SageMaker HyperPod operations with InstantStart HyperPod InstantStart is an open source control plane that composes Amazon EKS orchestration with the managed capabilities of Amazon SageMaker HyperPod. It drives the same guarded operations through both a web interface
GitHub BlogGitHubProject HydraFusion: Frontier quality via multi-model orchestration In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research preview in GitHub Copilot.
Stack Overflow Blog
Stack Overflow BlogGitHubHow to build a secure-by-default AI coding agent Ryan chats with Greg Jennings, VP of Engineering for AI Products at Anaconda, about what it takes to build a secure-by-default AI coding agent, why prompts shouldn't be treated as strict security guardrails, and how Anac
Vercel Blog
Vercel BlogToolsGPT 6 Astra now available on Vercel AI Gateway GPT 6 Astra from OpenAI is now available on AI Gateway. It is designed for long-running agentic work across software engineering, computer and browser use, scientific research, and professional workflows. Astra can navig
NVIDIA BlogSiliconSparks Fly: NVIDIA Accelerates Local AI at IFA 2026 Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are teaming up to provide faster inference and new tools that make agents easier to set up and run locally on NVIDIA hardware. New com
GitHub Blog
GitHub BlogGitHubGitHub Copilot app for Beginners: Run several agents at once Learn how to run parallel agents in the GitHub Copilot app, and experience the moment it stops feeling scary and starts feeling powerful.
Tom's Hardware AISiliconNvidia PAIR utility joins every GPU in your home into a cluster for agentic AI tasks — tool uses spare cycles to keep agent swarms from hammering one GPU Nvidia's Personal AI Router (PAIR) clustering utility lets agentic AI workloads take advantage of every spare GPU cycle on a home network, potentially making for faster execution and more private inference.
Nothing matches this filter yet.