Today's stories Nanbeige Releases Nanbeige4.3-33B, a 33B Open Agentic Coding Model M MarkTechPost 7h ago Outside evaluators found ways OpenAI’s agents could slip past its monitor T The Next Web 18h ago This week OpenAI Built a Giant Fake Internet for Its Agents to Use and Abuse Safely G Gizmodo 1d ago Microsoft Open-Sources Agensh: A Multi-Agent Harness for 1,024 Agents M MarkTechPost 1d ago Anthropic Joins the A.I. Agent Race With Claude Duet U T B +10 Covered by 13 sources 4d ago Anthropic says Mythos kept hacking even when it knew real people could get hurt B Business Insider 3d ago Meta’s Muse Is Going Gangbusters. But Where Is the Payoff? T The Wall Street Journal 3d ago Context Engineering (Agent Memory) for AI Agents Starts with Retrieval L LangChain 2d ago Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide A AWS Blog 2d ago Are We Near AGI? F Forbes 3d ago Who Will Your AI Agent Work For When Everyone Wants The Sale? F Forbes 3d ago Left alone with nothing to do, AI agents started playing T TechCrunch 3d ago OpenClaw creator puts last month’s token bill at $10M, The Register reports T The Next Web 3d ago TinyFish Breaks Down Agentic Search Architecture for Production AI Agents M MarkTechPost 3d ago Agentic AI Foundation adds four more open-source AI tools S SiliconANGLE 3d ago Third-party evaluators found vulnerabilities in OpenAI monitoring system during test pilot U C Covered by 2 sources 3d ago Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox H Hugging Face 3d ago Google Open-Sources Harness²: Self-Improving AI Agents Without Retraining K KDnuggets 4d ago Quoting Armin Ronacher S Simon Willison's Weblog 4d ago Donating Agent Skills to the Agentic AI Foundation S Simon Willison's Weblog 3d ago Agentic AI Foundation Adds Four Projects to Reach 10 in First Year U Unite.AI 4d ago OpenAI says an AI agent lied about disabling its safety monitoring system E T T +1 Covered by 4 sources 5d ago Zuckerberg Wants to Build a Giant Online Network of AI Agents G Gizmodo 4d ago OpenAI donates Open Responses, its spec for a common LLM API, to the Agentic AI Foundation T The New Stack (AI) 4d ago Vercel Labs Open-Sources fx: a Zig Coding Agent Designed to Be Embedded I InfoQ (AI, ML & Data) 4d ago The full context of the AI agent quote at the end of AI Gone Wild on Netflix L LessWrong 3d ago Your Next Customer Might Be An Agent. Here’s How To Build Your Brand For Both Humans And AI. C Crunchbase 4d ago Presentation: Actors for Agents: Patterns for Production AI I InfoQ (AI, ML & Data) 4d ago Agentic AI Doesn’t Usually Back Up Before Acting U Unite.AI 4d ago OpenAI’s most powerful AI models turned off safety monitoring – then lied about it Z ZDNet 4d ago Vercel Open-Sources durable-harness for Crash-Proof Coding Agents M MarkTechPost 4d ago NVIDIA Debuts OpenShell Reference Architecture for Agent Governance U Unite.AI 5d ago Claude Mods: Flipping the Harness Inside Out L Latent.Space 5d ago Trusting AI Agents Means Preserving Human Intent F Forbes 5d ago Glean Adds Headless Agent Building for Claude Code, Cursor and Codex U Unite.AI 5d ago Cloudflare Clairic P Product Hunt 5d ago 30 Months on the Exponential (in Charts) O One Useful Thing 6d ago Linkpost: Can a million AI agents create superintelligence? L LessWrong 5d ago [AINews] not much happened today L Latent.Space 6d ago MiniMax launches M3.1 Flash model, says it cuts AI agent costs by 70% U S T Covered by 3 sources 7d ago How I built my ‘everything’ app B Ben’s Bites 6d ago MIT’s AI agent society result holds up on consumer hardware T The Next Web 6d ago Intelli for ChatGPT & Claude P Product Hunt 6d ago Documents Reveal Military Plan for Agentic AI That Hacks U.S. Adversaries G Gizmodo 6d ago Making the internet better for AI agents might make it worse for everyone else M MIT Technology Review 6d ago MiniMax Just Launched M3.1 Flash: 428B MoE Agentic Model at $0.15/M Input M MarkTechPost 7d ago Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM A AWS Blog 7d ago Production-grade LLMs and agents: a field guide S StackOverflow 7d ago The Agentic Era Needs A Different Kind Of Memory F Forbes 7d ago LangChain vs. LlamaIndex vs. Building From Scratch: Here’s What I Suggest K KDnuggets 7d ago This month Context Management for Deep Agents L LangChain 12d ago August 2026: LangChain Newsletter — Managed Deep Agents, LLM Gateway, and More L LangChain Aug 27 AI Gateway logs now show session affinity V Vercel 7d ago Man’s Meta Muse Agent Sends Him Message So Bizarre That He Permanently Quits F Futurism 8d ago Google Open-Sources Harness2, a Recursive Agent Harnessing Framework M MarkTechPost 8d ago Websites are closing their doors to AI agents T The Verge 9d ago DeepSeek V4.1 Flash 1017 now available on AI Gateway V M Covered by 2 sources 9d ago Nvidia’s new Nemotron 3.5 Super VL is another step forward for US open-weight AI Z U P +4 Covered by 7 sources 11d ago Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore A AWS Blog 9d ago What will AI agents 'do'? | Infosys CTO Rafee Tarafdar | ET AI Podcast E ET AI (The Economic Times) 9d ago Showing the 60 most recent of 549 stories on Agentic Software Development