ππΌWelcome! In this short video, weβll show you how to get started with CAI, a cybersecurity oriented AI framework. CAI is specifically designed for cybersecurity use cases, aiming at semi- and fully-automating offensive and defensive security tasks.
-
0.0 - Launching CAI is super simple. . Just type βcaiβ in your terminal and hit Enter. Once CAI starts, youβll see a list of the most commonly used commands, along with some quick-start guides to help you understand the basics.
-
12.0 - CAI can also act as a regular command-line interface. To enter shell mode, just type /shell or use the $ prefix followed by your command.
-
25.0 - You could also type /help to get a list of features and how to use them.
-
33.0 - One of CAIβs most powerful features is the use of agents β pre-configured AI setups for specific tasks. To see available agents, use the command /agent. You can select one by typing /agent followed by the agent number. When you select an agent, CAI will display a full description of what it does and which tools it has access to.
-
45.0 - The next step is selecting the AI model you want to use. CAI supports over 300 LLMs, both open and commercial. In this example, weβll choose a free model: Qwen2.4-14B
-
60.0 - Now, weβll ask CAI to perform a simple network scan on our local router. CAI automatically starts running Nmap commands and shows you the output.
-
90.0 - β οΈ Keep in mind, this is just a basic example. CAI has been used successfully to find and exploit real-world vulnerabilities in bug bounty programs and even in corporate web apps. To learn more and see proof-of-concepts, visit my LinkedIn profile! To learn more and see proof-of-concepts, visit our profiles!.
More about it:
- π» source code: https://github.com/aliasrobotics/cai
- π paper: https://arxiv.org/pdf/2504.06017
- π§βπ€βπ§ community: https://discord.gg/fnUFcTaQAC