Topics

Every named tool, model, company, and protocol that has appeared in our coverage, ranked by how often it shows up. The recurring names are the story.

Claude Code 47 OpenAI 22 Anthropic 17 Codex 17 Agent Skills 15 DeepSeek Harness 12 Hugging Face 12 Model Context Protocol 12 Kimi K3 11 MCP 8 Claude Code auto mode 7 GPT-5.6 Sol 7 MCP 2026-07-28 7 METR 7 GPT-5.6-Cyber 6 Ollama 6 Anthropic Frontier Red Team 5 Claude Opus 5 5 GitHub Copilot 5 GLM-5.3 5 OpenAI Presence 5 Claude Code self-hosted environments 4 Claude Fable 5.1 4 Cloudflare Vulnerability Discovery and Remediation 4 Cordis 4 Cursor 4 Enterprise Frontier Safeguards 4 FreeToken 4 GLM 5.2 4 GPT-5.6 Luna 4 GPT-6 Astra 4 grok-build 4 LangChain 4 LangSmith Preview Builds 4 MAI-Cyber-1-Flash 4 Muse Glimmer 4 NVIDIA 4 OpenAI Codex 4 OpenAI Daybreak 4 ponytail 4 Prime Agent 4 QM 4 xAI 4 1Password for Claude 3 Admin plugin for ChatGPT Work and Codex 3 AgentForger 3 AI-Infra-Guard 3 AISLE 3 Amazon Bedrock AgentCore 3 archify 3 AWS 3 Busbar 3 Chain-of-thought monitoring 3 ChatGPT Ads 3 ChatGPT Atlas 3 Claude Security 3 Cloudflare BotBase 3 Cloudflare OAuth scope customization 3 Cloudflare OS 3 Cloudflare Wallets 3 cloudflare-computer 3 CopilotKit OpenBot 3 Gemini CLI 3 GitHub Copilot code review 3 GitHub Copilot in Microsoft Teams 3 Headlong 3 Hermes Agent 3 Jalapeño 3 LangSmith Engine 3 llama.cpp 3 mattpocock/skills 3 MCP 2026-07-28 specification 3 MemTrapBench 3 Munder Difflin 3 Open Secure AI Alliance 3 opencodex 3 OpenConnector 3 OpenWiki 0.4.0 3 Orca 3 pdf-inspector 3 Qwen3.8-27B 3 Trendshift 3 TurboFieldfare 3 unlazy 3 Adversa AI 2 AgentENV 2 AirLLM 2 alibaba/open-code-review 2 Amazon AI spend guardrails 2 Anthropic alignment and security update 2 Apodex 1.1 2 ARC-AGI-3 2 arcbox 2 arrayref supply-chain attack 2 Astra 2 autoharness 2 Azure DevOps MCP server 2 block/buzz 2 book-to-skill 2 celld 2 ChatGPT desktop app 2 ChatGPT for Academic Researchers 2 ChatGPT Voice 2 ChatGPT Work 2 Cisco Antares 2 Claude 2 Claude Agent SDK 2 Claude apps gateway 2 Claude Code 2.1.259 2 Claude Compliance API 2 Claude Cowork 2 Claude for Teachers 2 Claude Mythos 5 2 Claude Mythos 5.1 2 Claude Mythos Preview 2 Claude text watermarking 2 Claude voice mode 2 Cloudflare 2 Cloudflare Bot Preference Sync 2 Cloudflare Workers 2 Codex Micro 2 Codex Multi-Agent V2 2 Codex Security CLI 2 ContextPilot 2 CoreBreak 2 Cursor Origin 2 CVE-2026-85046 2 Dario Amodei open-weights position 2 DeepSeek-V4-Pro 2 DeepSeek-V4.1-Flash 2 EnvHarness 2 Environment Evolution for Terminal Agents 2 ExploitGym 2 Firecrawl 2 FrontierAgent 2 Gemini 3.5 Flash Cyber 2 Gemini 3.5 Pro 2 Gemini 3.6 Flash 2 Gemini 3.7 Flash 2 Gemini 3.8 Flash Cyber 2 GitHub Bug Bounty 2 GitHub Copilot in Slack 2 GLM-5.3-Flash 2 Google 2 Google ADK for Python 2 Google Research 2 GPT-5.6 Sol Ultrafast 2 GPT-Live 2 GPT-Red 2 Grok Bot 2 hallmark 2 harness-engineering 2 Hugging Face agent intrusion 2 Inference hooks 2 Inkling 2 Irregular 2 Kiro Crew 2 Kitesurf 2 LangChain Managed Deep Agents 2 LangChain v1.4.0 2 Level1Techs inference precision study 2 Managed Agents 2 MCP Roadmap 2026 2 Memmy Agent 2 Mercury Spend 2 Microsoft Copilot 2 Microsoft Foundry 2 Model Hardware Standard 2 NanoGPT Speedrun Frontier 2 npm trusted publishing 2 okf-agent-memory 2 Omarchy 2 oomol-lab 2 Open Knowledge Format 2 open-kritt 2 OpenAI Hugging Face incident report 2 OpenAI Preparedness Framework 2 OpenAI Private Safety Processing 2 OpenClaw 2 OpenHuman 2 OpenMAIC 2 OpenWorker 2 OWASP Agentic Skills Top 10 2 OWASP MCP Top 10 2 Palmyra X6 2 PenguinHarness 2 Pinecone Nexus 2 Project HydraFusion 2 Project Perception 2 Qwen-MM-Plugins 2 Redwood Research 2 reverse-skill 2 Shieldstral 2 Simon Willison 2 SKILL.md 2 Slack Code 2 Snyk ToxicSkills 2 sol-advisor 2 SQLite Cloud 2 StateM 2 Stripe acquires OpenRouter 2 Strix 2 Tencent Hy4-preview 2 Terminal-Bench 2 Terminal-Universe 2 The Defender's Window 2 Thinking Machines 2 Thinkingbox 2 Trajectory Labs 2 Trend Micro 2 Tristan Buckmaster 2 Ultrafast mode 2 Unsloth Desktop 2 VitaBench 2.0 2 WASTE 2 WASTE inference engine 2 watermarks-remover 2 Webcmd 2 WikiSkill 2 x402 2 Y Combinator 2 Zenity Labs 2 A.X K2 1 AdaptiveMem 1 AG-UI protocol 1 Agent Cards 1 Agent Client Protocol 1 Agent Lightning v1.0 1 Agent Plugins 1.0 1 Agent Skills specification 1 agent-browser 1 AgentCore Runtime Instances 1 AgentDB 1 AgentFlow 1 Agentic AI Foundation 1 Agentic attacker 1 AgentR 1 agentskills.io 1 agentskills/agentskills 1 AI Kill Switch Act 1 AI Now Friendly Fire exploit 1 AI Security Institute incident report 1 AI skills 1 ai-agent-book 1 aisuite 1 ALFWorld 1 Alibaba 1 Alibaba Cloud 1 Alibaba Cloud Agent Native Cloud 1 Alibaba Qwen 1 allowedMcpServers 1 Alpine Linux 1 Alterion Draco 1 Amazon Bedrock 1 Amazon Bedrock Agents Classic 1 Amazon Kiro 1 Amazon Nova wind-down 1 An Alien Mind 1 Andrew Ng 1 Andrey Mikhaylov 1 Anil Madhavapeddy 1 Anthropic Agent Memory 1 Anthropic August 2026 Risk Report 1 Anthropic content marking 1 Anthropic Frontier Red Team cyber-eval incidents 1 Anthropic Frontier Red Team cybersecurity eval disclosure 1 Anthropic Frontier Red Team eval incidents 1 Anthropic Messages API 1 Anthropic Model Hardware Standard 1 Anthropic Mythos 1 Anthropic open-weights position 1 Anthropic Skills 1 Anthropic-Cybersecurity-Skills 1 anthropics/commerce-agents 1 Antigravity 1 anydoc 1 Anyscale 1 anywhere-labs 1 Apollo Research 1 Apple M5 Ultra 1 Apple Virtualization.framework 1 ARC Prize 1 arrayref 1 Atlassian Rovo 1 Atlassian Rovo exfiltration 1 AutoHedge 1 awesome-agent-skills 1 awesome-design-md 1 AWS Bedrock AgentCore 1 Axonius 1 Axonius MCP Server 1 Azure SRE Agent 1 Bankruptcy Code Section 363 1 Bedrock AgentCore 1 BigCodeBench 1 bitemporal knowledge graph 1 Blitz 1 C2PA 1 CAC Implementation Opinions 1 Cactus Compute 1 Calif WeWorm 1 California SB 942 1 career-ops 1 CaSKG 1 Catherine Cassell 1 CEL policy 1 Censys 1 Cequence AI Gateway 1 Cerebras 1 Cerebras CS-4 1 Certificate Transparency 1 ChainDrop 1 ChatGPT 1 ChatGPT for Teens 1 ChatGPT Workspace Agents 1 Chrome DevTools for agents 1 Chrome DevTools Protocol 1 chrome-devtools-mcp 1 Chromium 1 Chronicle 1 CISA Known Exploited Vulnerabilities Catalog 1 CitroLabs 1 CL4R1T4S 1 Claude Code 2.1.222 1 Claude Code 2.1.237 1 Claude Code 2.1.238 1 Claude Code runner 1 Claude Commerce Agents 1 Claude Enterprise 1 Claude Fable 5 1 Claude for Chrome 1 Claude Haiku 4.5 1 Claude Opus 4.6 1 Claude Opus 4.8 1 Claude Platform 1 Claude Sonnet 5 pricing 1 claude-obsidian 1 Claudette 1 CLI-Anything 1 CLI-Hub 1 Cloudflare Adaptive Intelligence 1 Cloudflare Agents SDK 1 Cloudflare Agents Week 1 Cloudflare Agents Week 2026 1 Cloudflare Browser Run 1 Cloudflare Durable Objects 1 Cloudflare Kitesurf 1 Cloudflare Quick Tunnel 1 Cloudflare task-based OAuth consent 1 cloudflare.pay 1 Code review 1 code-review-graph 1 CodeMender 1 Codex 0.147.0 1 Codex app server 1 Codex Auto-review 1 Codex CLI 1 Codex CLI 0.145.0 1 Codex CLI 0.149.0 1 Codex CLI 0.152.0 1 codex mcp-server 1 Codex plugin for Claude Code 1 Codex-Dream-Skin 1 codex-host 1 codex-plugin-cc 1 codex-with-chatgpt 1 Coding agents 1 cohttp 1 collusion.wiki 1 Compliance API 1 Composio 1 Computer History 1 Connections 1 Continual Harness 1 Copilot code review 1 Corsair 1 crates.io 1 Credential Vault 1 CryptanalysisBench 1 Cua Metal capability shim 1 curl 1 Cursor Router 1 CVE-2025-59829 1 CVE-2025-62593 1 CVE-2026-25724 1 CVE-2026-59726 1 CyberGym 1 Cyera 1 Dan Luu agentic testing eval 1 Daniel Stenberg 1 DashScope 1 Databricks 1 Daybreak Blue 1 Daybreak Red 1 Debian 1 DeepLethe 1 DeepSeek 1 DeepSeek context caching 1 DeepSeek-Reasonix 1 deepseek-v4-flash-vision-exp 1 deltafin 1 Deno 1 Desert Ant Labs 1 DESIGN.md 1 different-ai openwork 1 Digital Birth Certificates 1 DisCo 1 Discovery Loop 1 Docker 1 Docling 1 Docusign MCP Server 1 dsh 1 DSH Desktop 1 Durable Objects 1 duty1g/x64dbg-mcp-server 1 E2B 1 earendil-works 1 Edit fidelity 1 ego lite 1 ego-browser 1 elder-plinius 1 Electron 1 Elie Habib 1 Enkrypt AI 1 Enterprise-Managed Authorization 1 EU AI Act Article 50 1 European Commission 1 eval-engineering skill 1 Explicit handle pattern 1 Fable 5 export order 1 fable51-worlds 1 Felony Bench 1 Fermat's Last Theorem formalization 1 Firecracker 1 Firecrawl pdf-inspector 1 firecrawl/anydoc 1 FlashML 1 FpSan 1 FrontierChallenge 1 full-stack-fastapi-template 1 funes 1 Gatekeepers 1 Gemini 3.5 Transcribe 1 Gemini agentic video 1 Gemini API Managed Agents 1 Gemini Robotics 1.6 1 Gemini Robotics 2 1 Gemini Spark Chrome auto browse 1 Gemma 4 26B-A4B 1 get-bb/bb 1 gigatoken 1 GitHub Advanced Security 1 GitHub Copilot CLI 1 GitHub Copilot cloud agent 1 GitHub Copilot content exclusions 1 GitHub Copilot in Slack and Teams 1 GitHub global model policy 1 Go 1 Gondolin 1 Google ADK 2.5.0 1 Google Agent Development Kit 1 Google Credentio 1 Google DeepMind 1 Google DeepMind leadership change 1 Google Stitch 1 GPT-5.4 1 GPT-5.6 1 GPT-5.6 in Kiro 1 GPT-5.6 Luna price cut 1 GPT-5.6 price cut 1 GPT-5.6 Terra 1 graphify 1 Guideflow 1 h3.c 1 h4ckf0r0day/obscura 1 HackerOne Signal 1 Haiku 4.5 1 Harbor 1 HarnessDev 1 HAWK signature scheme 1 Headroom 1 Health in ChatGPT 1 HealthKit 1 HeyGen Hyperframes 1 HIVE.md 1 HKUDS 1 holaOS 1 Holistic Agent Leaderboard 1 Host daemon 1 Hugging Face incident 1 IBM Cost of a Data Breach 2026 1 Identity-Aware AI Gateway 1 iFixAi 1 iMe 1 Immad Akhund 1 InferenceX 1 Interim Measures for AI Anthropomorphic Interactive Services 1 iSH 1 Jakub Pachocki 1 JFrog Agent Skills Registry 1 JFrog Artifactory 1 Johann Rehberger 1 JuliusBrussee/caveman 1 just-bash 1 K-Dense AI 1 K2 Horizon 1 Kenton Varda 1 keyv 1 keyv npm worm 1 Koishi 1 kvcache-ai 1 LangChain deepagents 1 LangChain OpenWiki 1 langchain.mcp 1 LangGraph 1 Laude Institute 1 Lean 4 1 LEDGER benchmark 1 LEGO-RL 1 Leonxlnx 1 Leonxlnx/unlazy 1 Levent Alpöge 1 Linear AI usage data 1 Linear How Teams Build 1 LiteLLM 1 little-lm 3.8B 1 llm-space 1 LMSM 1 LongCat-2.0 1 LongMemEval 1 LoopX 1 Lume 1 Magnitude 1 MAI-Transcribe-2 1 managedMcpServers 1 Manager thread 1 Mandiant M-Trends 2026 1 Manifold Security 1 Manus 1 Marco Bambini 1 MCP 2024-11-05 1 MCP 2026-07-28 Spec 1 MCP Apps 1 MCP connector 1 MCP Dev Summit Seoul 1 MCP Roadmap 1 MCP tool annotations 1 MDASH 1 meat 1 Meituan LongCat 1 Memory Tree 1 MEMORY.md 1 MemOS 1 MemPalace 1 MemTensor 1 Mercor 1 Mercury 1 Mercury 2.5 1 Meta Muse 1 Meta Superintelligence Labs 1 Microsoft 1 Microsoft Agent Framework 1 Microsoft AI 1 Microsoft Copilot Studio 1 Microsoft Defender 1 Microsoft Security 1 Microsoft Security Response Center 1 Microsoft SkillOpt 1 microsoft/tgrep 1 Mind viruses preprint 1 Ministral-3-3B 1 Mistral 1 Mistral AI 1 Mistral Vibe 1 MITRE ATT&CK 1 MITRE Fight Fraud Framework 1 MLX 1 Mojo 1.0 1 MoonEP 1 Moonshine 1 Nanako Tsai 1 Navier-Stokes Millennium Prize Problem 1 Needle 2 1 Nemotron 3.5 Lightning 1 Netzilo 1 Nevermined 1 no-ai-slop 1 Noma Security 1 Nous Research 1 npm 1 npx skills 1 NVFP4 1 NVIDIA Cosmos 3 Edge 1 NVIDIA Labs Object-Oriented Agents (NOOA) 1 NVIDIA NeMo Switchyard 1 NVIDIA NOOA 1 NVIDIA OpenShell 1 NVIDIA Personal AI Router 1 NVIDIA SkillSpector 1 NVIDIA Switchyard 1 Oasis Security 1 Obsidian 1 Ode 1 OmniRoute 1 On the Bench 1 Open Agent Skill Standard 1 Open Interpreter 1 Open Knowledge Format v0.2 1 open-connector 1 OpenAI Agent Builder 1 OpenAI Astra 1 OpenAI Black Hat agent message board 1 OpenAI Computer History 1 OpenAI Daybreak for Frontline Defenders 1 OpenAI Enterprise Signals 1 OpenAI Forward Deployed Engineers 1 OpenAI GPT-5.6 efficiency post 1 OpenAI Navier-Stokes 1 OpenAI paid usage resets 1 OpenAI Preparedness team 1 OpenAI Research Acceleration 1 openai/codex-security 1 openai/NavierStokesAndEuler 1 OpenCode 1 opendataloader-bench 1 OpenMinis 1 OpenSandbox 1 OpenViking 1 OpenWiki 1 OpenWork 1 Ornith-1.5 1 pacifio/atlas 1 Pacing the Frontier 1 Parameter-to-Prompt 1 Paritok-4B-v1 1 Patterns and problems in multiagent systems 1 Peking University 1 Perplexity Sonar 1 Peter Yang 1 pgvector 1 Pi agent harness 1 Pillar Security 1 PILOT 1 Pilot Protocol 1 Playwright 1 Podman 1 Poolside Laguna S 2.1 1 Portal by Spotify 1 Pranshu Parmar 1 Praxist 1 prefix cache 1 Preserved Thinking 1 Prime Intellect 1 Private Safety Processing 1 proc-macro1 1 Project Glasswing 1 Prompt injection 1 Property-based testing 1 Puppeteer 1 PyPI 1 Quantization-Aware Healing 1 QuickJS 1 Qwen 1 Qwen 3.8-Max-Preview 1 Qwen3 1 Qwen3.6-27B 1 Qwen3.8-2.4T-A95B 1 Qwen3.8-Max 1 Qwen3.8-Max License 1 Ray 1 Ray CVE-2025-62593 1 ReasoningBank 1 redhat-et 1 Repo-To-Skill 1 Responses API 1 RFC 6749 1 ripgrep 1 ripwire 1 RovoBlast 1 Ruflo 1 Ruflo CVE-2026-59726 1 Rust Security Response Team 1 rust-lang LLM policy 1 Ryan Dahl 1 SafeDep 1 Sandstorm.io 1 Santiago Fernandez de Valderrama Aparicio 1 SARIF 1 scientific-agent-skills 1 SemiAnalysis 1 SEP-2567 1 sepia 1 Shared Responsibility Model 1 ShareLock 1 shellm 1 Simple Attention Network 1 skill-doctor 1 SkillFortify 1 SkillOpt 1 Slack 1 SlopCodeBench 1 SOUL.md 1 SpaceX 1 SpaceX Anysphere acquisition 1 spawn_agent 1 Spirit Airlines 1 Spirit Airlines data auction 1 stablyai Orca 1 Standard Webhooks 1 StateLM 1 Stealing Reasoning Traces 1 Stealing Reasoning Traces from Proprietary LLM APIs 1 StepGuard 1 Stop Rogue AI Act 1 StoryScope 1 Stripe OpenRouter acquisition 1 sv-number/skills 1 SWE-bench Verified 1 SynthID audio provenance 1 systemd 1 tau-tau-Bench 1 Tencent Cloud 1 Tencent Youtu Lab 1 Tencent Zhuque Lab 1 TencentDB Agent Memory 1 Tenet Security 1 Terence Tao 1 Terminal-Bench 2.1 1 Tessl Registry 1 The Harness Effect 1 The Swarm Corporation 1 Theseus Infrastructure 1 THU-MAIC 1 Tiny Humans AI 1 tl;dv disclosure 1 tokentab 1 Tool search 1 Trail of Bits 1 Tranco 1 Trellner Research 1 Trellner TR-2026-009 1 Triton 1 TrueForge 1 trycua/cua 1 UK AI Security Institute 1 Unit 42 1 Unit 42 autonomous attack campaign 1 unslothai/unsloth 1 Utopia 1 Varonis Threat Labs 1 Vercel 1 Vercel AI SDK 1 Vercel Labs 1 vercel-labs/scriptc 1 video-use 1 viking:// protocol 1 VikingMem 1 vLLM 1 VoiceStudio 1 Volcengine 1 VoltAgent 1 Waggle 1 WebMCP 1 WhatsApp MCP CVE 1 wigolo 1 witr 1 Wiz Red Agent 1 WorldMonitor 1 Writer Agent Harness 1 Writer Palmyra X6 1 x-algorithm 1 x64dbg 1 Y Combinator QM 1 Z.ai 1 Zero Data Retention 1 zhaoxuya520 reverse-skill 1 Zig 1 ZJUNLP 1

Beats

The standing beats we file everything under.

agent-infrastructure 215 agent-security 209 agent-harness 174 ai-skills 97 frontier-models 96 local-ai 90 claude-code 88 multi-agent 70 mcp 66 agent-memory 56 codex 56 agent-identity 41 privacy 37 mcp-security 29 regulation 28 rag 13 agent-payments 10 fine-tuning 9 funding 5 supply-chain 1