[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:adrian":3},"\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"assets\u002Fadrian-logo-dark.png\">\u003C\u002Fsource>\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fsecureagentics\u002Fadrian\u002FHEAD\u002Fassets\u002Fadrian-logo-light.png\" alt=\"Adrian by Secure Agentics\" width=\"360\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\u003Ch3>Agent attacks slip past static analysis and network monitoring.\u003C\u002Fh3>\n\u003Cp align=\"center\">\u003Cb>Adrian catches them at runtime, by watching what the agent actually does (its actions and its reasoning) and stepping in before it acts. Open source, free forever.\u003C\u002Fb>\u003C\u002Fp>\u003Cp align=\"center\">\u003Cb>+35% detection accuracy · 4x more nuanced attacks caught\u003C\u002Fb> vs behaviour-only monitoring (\u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2503.11926\" rel=\"nofollow ugc noopener\">OpenAI & DeepMind research\u003C\u002Fa>)\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsecureagentics\u002FAdrian\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fsecureagentics\u002FAdrian?style=social\" alt=\"Stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsecureagentics\u002Fadrian\u002Fblob\u002FHEAD\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicence-Apache--2.0-blue.svg\" alt=\"Licence\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fapp.adrian.secureagentics.ai\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDashboard-Sign%20Up-22C55E\" alt=\"Dashboard\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fadrian-sdk\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fadrian-sdk.svg\" alt=\"PyPI\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FVq2VyYrw8Z\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join-5865F2?logo=discord&logoColor=white\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fsecure-agentics\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinkedIn-Follow-0A66C2?logo=linkedin&logoColor=white\" alt=\"LinkedIn\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.producthunt.com\u002Fproducts\u002Fadrian?embed=true&utm_source=badge-featured&utm_medium=badge&utm_campaign=badge-adrian\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FProduct%20Hunt-Featured-DA552F?logo=producthunt&logoColor=white\" alt=\"Product Hunt\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\u003Ci>⭐ If you think agents need a runtime security layer, star the repo. It is how new people find Adrian, and how we know to keep building it in the open.\u003C\u002Fi>\u003C\u002Fp>\u003Chr \u002F>\n\u003Cp>Adrian is an open-source, \u003Ca href=\"https:\u002F\u002Faarm.dev\" rel=\"nofollow ugc noopener\">AARM-aligned\u003C\u002Fa> runtime security monitoring and control engine for AI agents. It analyses both agent activity logs (tool calls, actions, outputs) and reasoning traces to detect malicious, misaligned, or out-of-remit behaviour, and optionally intervene in-flight. SDKs are available for Python (LangChain) and TypeScript (\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsecureagentics\u002Fadrian\u002Fblob\u002FHEAD\u002Fsdk\u002Ftypescript\u002FREADME.md\" rel=\"nofollow ugc noopener\">sdk\u002Ftypescript\u002FREADME.md\u003C\u002Fa>), plus a native \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsecureagentics\u002Fadrian\u002Fblob\u002FHEAD\u002Fintegrations\u002Fclaude-code\u002FREADME.md\" rel=\"nofollow ugc noopener\">Claude Code plugin\u003C\u002Fa> that secures every tool call from your terminal.\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>\u003Cstrong>🆕 Claude Code plugin - now live.\u003C\u002Fstrong> Drop Adrian into Claude Code and every tool call is classified in real time, with risky actions blocked or held for your approval right in the terminal. No code changes: install with \u003Ccode>\u002Fplugin marketplace add secureagentics\u002FAdrian\u003C\u002Fcode> then \u003Ccode>\u002Fadrian-init\u003C\u002Fcode>. Full guide: \u003Cstrong>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fsecureagentics\u002Fadrian\u002Fblob\u002FHEAD\u002Fintegrations\u002Fclaude-code\u002FREADME.md\" rel=\"nofollow ugc noopener\">integrations\u002Fclaude-code\u002FREADME.md\u003C\u002Fa>\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdocs.adrian.secureagentics.ai\" rel=\"nofollow ugc noopener\">Documentation\u003C\u002Fa>  • \n  \u003Ca href=\"https:\u002F\u002Fapp.adrian.secureagentics.ai\" rel=\"nofollow ugc noopener\">Dashboard\u003C\u002Fa>  • \n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FVq2VyYrw8Z\" rel=\"nofollow ugc noopener\">Discord\u003C\u002Fa>  • \n  \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fsecure-agentics\" rel=\"nofollow ugc noopener\">LinkedIn\u003C\u002Fa>\n\u003C\u002Fp>\u003Cblockquote>\n\u003Cp>\u003Cstrong>▶️ See it in action:\u003C\u002Fstrong> Adrian catches an agent going out-of-remit in real time and steps in before the action lands.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fba50e6e4-fe3e-47b2-aa69-2902e1ef2924\" rel=\"nofollow ugc noopener\">https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fba50e6e4-fe3e-47b2-aa69-2902e1ef2924\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Csup>New to Adrian? Check out the \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=NkEISlRhyFs\" rel=\"nofollow ugc noopener\">Launch Video\u003C\u002Fa>.\u003C\u002Fsup>\u003C\u002Fp>\n\u003Ch2>Why Adrian is different\u003C\u002Fh2>\n\u003Cp>Most agent monitoring stops at activity logs: APIs, MCP, DB interactions, tool calls, etc. Adrian enhances this by also analysing the agent's reasoning: understanding \u003Cem>why\u003C\u002Fem> it took an action, under what context, and what it is planning on doing next. Combining behaviour and reasoning analysis like this is exactly what the [Open\u003C\u002Fp>\n",1785276847915]