aliasrobotics/cai

Cybersecurity AI (CAI)

Professional Edition with unlimited alias1 tokens | 📊 View Benchmarks | 🚀 Learn More

🔓 Community Edition Research & Learning · Perfect for Researchers & Students pip install cai-framework

✅ Free for research 🤖 300+ AI models 🌍 Community driven 📚 Open source 🔧 Extensible framework

🚀 Professional Edition Enterprise & Production · €350/month · Unlimited alias1 Tokens

→ Upgrade to PRO

⚡ alias1 model - ∞ unlimited tokens 🚫 Zero refusals - Unrestricted AI 🏆 Beats GPT-5 in CTF benchmarks 🛡️ Professional support included 🇪🇺 European data sovereignty

CAI PRO w/ alias1 model outperforms GPT-5 in AI vs AI cybersecurity benchmarks | View Full Benchmarks →

-->

Cybersecurity AI (CAI) is a lightweight, open-source framework that empowers security professionals to build and deploy AI-powered offensive and defensive automation. CAI is the de facto framework for AI Security, already used by thousands of individual users and hundreds of organizations. Whether you're a security researcher, ethical hacker, IT professional, or organization looking to enhance your security posture, CAI provides the building blocks to create specialized AI agents that can assist with mitigation, vulnerability discovery, exploitation, and security assessment.

🔓 Run CAI without an Alias API Key (CAI_LICENSE_OFF)

CAI can run without an ALIAS_API_KEY (i.e. without an Alias Robotics license) by setting the environment variable CAI_LICENSE_OFF=1.

When CAI_LICENSE_OFF is set to 1, true, or yes:

• The startup license check is bypassed — no ALIAS_API_KEY is required.
• CAI runs in open-source mode and update operations target the public PyPI cai-framework package instead of the private Alias package index.
• You can use any other supported model provider (OpenAI, Anthropic, DeepSeek, Ollama, etc.) by configuring CAI_MODEL and the corresponding provider API key.

Quick start without a license:

export CAI_LICENSE_OFF=1
cai

Or inline:

CAI_LICENSE_OFF=1 cai

Note: The alias1 model still requires a valid ALIAS_API_KEY. CAI_LICENSE_OFF only bypasses the framework's license gate — it does not grant access to Alias-hosted models.

Key Features:

• 🤖 300+ AI Models: Support for OpenAI, Anthropic, DeepSeek, Ollama, and more
• 🔧 Built-in Security Tools: Ready-to-use tools for reconnaissance, exploitation, and privilege escalation
• 🏆 Battle-tested: Proven in HackTheBox CTFs, bug bounties, and real-world security case studies
• 🎯 Agent-based Architecture: Modular framework design to build specialized agents for different security tasks
• 🛡️ Guardrails Protection: Built-in defenses against prompt injection and dangerous command execution
• 📚 Research-oriented: Research foundation to democratize cybersecurity AI for the community

[!NOTE] Read the technical report: CAI: An Open, Bug Bounty-Ready Cybersecurity AI An HTML reading edition with figures and references is maintained by the Robot Cybersecurity Lab.

For further readings, refer to our impact and CAI citation sections.

Robotics - CAI and alias1 on: Unitree G1 Humanoid Robot	OT - CAI and alias1 on: Dragos OT CTF 2025
CAI uncovers vulnerabilities and privacy violations in Unitree G1 humanoid robots including unauthorized telemetry transmission to China-related servers, exposed RSA keys with world-writable permissions, and potential surveillance capabilities violating GDPR and international privacy laws.	CAI powered by alias1, demonstrates exceptional performance in operational technology cybersecurity by achieving a Top-10 ranking in the Dragos OT CTF 2025. The AI agent reached Rank 1 during competition hours 7-8, completed 32 of 34 challenges, and maintained a 37% velocity advantage over top human teams.

IT (Bug Bounty) - CAI on: HackerOne Platform	OT - CAI and alias0 on: Ecoforest Heat Pumps
HackerOne's top engineers leverage CAI to explore next-gen agentic AI architectures and build their own security products. CAI's Retester agent directly inspired HackerOne's AI-powered Deduplication Agent, now deployed in production to handle millions of vulnerability reports at scale.	CAI discovers critical vulnerability in Ecoforest heat pumps allowing unauthorized remote access and potential catastrophic failures. AI-powered security testing reveals exposed credentials and DES encryption weaknesses affecting all of their deployed units across Europe.

Robotics - CAI and alias0 on: Mobile Industrial Robots (MiR)	IT (Web) - CAI and alias0 on: Mercado Libre's e-commerce
CAI-powered security testing of MiR (Mobile Industrial Robot) platform through automated ROS message injection attacks. This study demonstrates how AI-driven vulnerability discovery can expose unauthorized access to robot control systems and alarm triggers.	CAI-powered API vulnerability discovery at Mercado Libre through automated enumeration attacks. This study demonstrates how AI-driven security testing can expose user data exposure risks in e-commerce platforms at scale.

OT - CAI and alias0 on: MQTT broker	IT (Web) - CAI and alias0 on: PortSwigger Web Security Academy
CAI-powered testing exposed critical flaws in an MQTT broker within a Dockerized OT network. Without authentication, CAI subscribed to temperature and humidity topics and injected false values, corrupting data shown in Grafana dashboards.	CAI-powered race condition exploitation in file upload vulnerability. This study demonstrates how AI-driven security testing can identify and exploit timing windows in web applications, successfully uploading and executing web shells through automated parallel requests.

[!WARNING] :warning: CAI is in active development, so don't expect it to work flawlessly. Instead, contribute by raising an issue or sending a PR.

Access to this library and the use of information, materials (or portions thereof), is ** not intended, and is prohibited, where such access or use violates applicable laws or regulations**. By no means the authors encourage or promote the unauthorized tampering with running systems. This can cause serious human harm and material damages.

*By no means the authors of CAI encourage or promote the unauthorized tampering with compute systems. Please don't use the source code in here for cybercrime. Pentest for good instead *. By downloading, using, or modifying this source code, you agree to the terms of the LICENSE and the limitations outlined in the DISCLAIMER file.

:bookmark: Table of Contents

• Cybersecurity AI (CAI)
• :bookmark: Table of Contents
• 🎯 Impact
• 🏆 Competitions and challenges
• 📊 Research Impact
• 📚 Research products: Cybersecurity AI
• PoCs
• Motivation
• :bust_in_silhouette: Why CAI?
• Ethical principles behind CAI
• Closed-source alternatives
• Learn - CAI Fluency
• :nut_and_bolt: Install
• OS X
• Ubuntu 24.04
• Ubuntu 20.04
• Windows WSL
• Android
• :nut_and_bolt: Setup .env file
• 🔹 Custom OpenAI Base URL Support
• :triangular_ruler: Architecture:
• 🔹 Agent
• 🔹 Tools
• 🔹 Handoffs
• 🔹 Patterns
• 🔹 Turns and Interactions
• 🔹 Tracing
• 🔹 Guardrails
• 🔹 Human-In-The-Loop (HITL)
• :rocket: Quickstart
• Environment Variables
• OpenRouter Integration
• Azure OpenAI
• MCP
• Development
• Contributions
• Optional Requirements: caiextensions
• :information_source: Usage Data Collection
• Reproduce CI-Setup locally
• FAQ
• Citation
• Acknowledgements
• Academic Collaborations

🎯 Impact

🏆 Competitions and challenges

📊 Research Impact

• Pioneered LLM-powered AI Security with PentestGPT, establishing the foundation for the Cybersecurity AI research domain

• Established the Cybersecurity AI research line with 8 papers and technical reports, with active research collaborations

• Demonstrated 3,600× performance improvement over human penetration testers in standardized CTF benchmark evaluations

• Identified CVSS 4.3-7.5 severity vulnerabilities in production systems through automated security assessment

• Democratization of AI-empowered vulnerability research: CAI enables both non-security domain experts and experienced researchers to conduct more efficient vulnerability discovery, expanding the security research community while empowering small and medium enterprises to conduct autonomous security assessments

• Systematic evaluation of large language models across both proprietary and open-weight architectures, revealing substantial gaps between vendor-reported capabilities and empirical cybersecurity performance metrics

• Established the autonomy levels in cybersecurity and argued about autonomy vs automation in the field

• Collaborative research initiatives with international academic institutions focused on developing cybersecurity education curricula and training methodologies

• Contributed a comprehensive defense framework against prompt injection in AI security agents: developed and empirically validated a multi-layered defense system that addresses the identified prompt injection issues

• Explord the Cybersecurity of Humanoid Robots with CAI and identified new attack vectors showing how it (a) operates simultaneously as a covert surveillance node and (b) can be purposed as an active cyber operations platform

📚 Research products: Cybersecurity AI

CAI, An Open, Bug Bounty-Ready Cybersecurity AI	The Dangerous Gap Between Automation and Autonomy	CAI Fluency, A Framework for Cybersecurity AI Fluency	Hacking the AI Hackers via Prompt Injection

Humanoid Robots as Attack Vectors	The Cybersecurity of a Humanoid Robot	Evaluating Agentic Cybersecurity in Attack/Defense CTFs	CAIBench: A Meta-Benchmark for Evaluating Cybersecurity AI Agents

Extended HTML reading editions: CAI · CAIBench · Humanoid robots as attack vectors · The cybersecurity of a humanoid robot · Hacking consumer robots in the AI era

PoCs

CAI with alias0 on ROS message injection attacks in MiR-100 robot	CAI with alias0 on API vulnerability discovery at Mercado Libre

CAI on JWT@PortSwigger CTF — Cybersecurity AI	CAI on HackableII Boot2Root CTF — Cybersecurity AI

More case studies and PoCs are available at https://aliasrobotics.com/case-studies-robot-cybersecurity.php.

Motivation

:bust_in_silhouette: Why CAI?

The cybersecurity landscape is undergoing a dramatic transformation as AI becomes increasingly integrated into security operations. We predict that by 2028, AI-powered security testing tools will outnumber human pentesters. This shift represents a fundamental change in how we approach cybersecurity challenges. AI is not just another tool - it's becoming essential for addressing complex security vulnerabilities and staying ahead of sophisticated threats. As organizations face more advanced cyber attacks, AI-enhanced security testing will be crucial for maintaining robust defenses.

This work builds upon prior efforts¹ and similarly, we believe that democratizing access to advanced cybersecurity AI tools is vital for the entire security community. That's why we're releasing Cybersecurity AI (CAI) as an open source framework. Our goal is to empower security researchers, ethical hackers, and organizations to build and deploy powerful AI-driven security tools. By making these capabilities openly available, we aim to level the playing field and ensure that cutting-edge security AI technology isn't limited to well-funded private companies or state actors.

Bug Bounty programs have become a cornerstone of modern cybersecurity, providing a crucial mechanism for organizations to identify and fix vulnerabilities in their systems before they can be exploited. These programs have proven highly effective at securing both public and private infrastructure, with researchers discovering critical vulnerabilities that might have otherwise gone unnoticed. CAI is specifically designed to enhance these efforts by providing a lightweight, ergonomic framework for building specialized AI agents that can assist in various aspects of Bug Bounty hunting - from initial reconnaissance to vulnerability validation and reporting. Our framework aims to augment human expertise with AI capabilities, helping researchers work more efficiently and thoroughly in their quest to make digital systems more secure.

Ethical principles behind CAI

You might be wondering if releasing CAI in-the-wild given its capabilities and security implications is ethical. Our decision to open-source this framework is guided by two core ethical principles:

1. Democratizing Cybersecurity AI: We believe that advanced cybersecurity AI tools should be accessible to the entire security community, not just well-funded private companies or state actors. By releasing CAI as an open source framework, we aim to empower security researchers, ethical hackers, and organizations to build and deploy powerful AI-driven security tools, leveling the playing field in cybersecurity.

2. Transparency in AI Security Capabilities: Based on our research results, understanding of the technology, and dissection of top technical reports, we argue that current LLM vendors are undermining their cybersecurity capabilities. This is extremely dangerous and misleading. By developing CAI openly, we provide a transparent benchmark of what AI systems can actually do in cybersecurity contexts, enabling more informed decisions about security postures.

CAI is built on the following core principles:

• Cybersecurity oriented AI framework: CAI is specifically designed for cybersecurity use cases, aiming at semi- and fully-automating offensive and defensive security tasks.
• Open source, free for research: CAI is open source and free for research purposes. We aim at democratizing access to AI and Cybersecurity. For professional or commercial use, including on-premise deployments, dedicated technical support and custom extensions reach out to obtain a license.
• Lightweight: CAI is designed to be fast, and easy to use.
• Modular and agent-centric design: CAI operates on the basis of agents and agentic patterns, which allows flexibility and scalability. You can easily add the most suitable agents and pattern for your cybersecuritytarget case.
• Tool-integration: CAI integrates already built-in tools, and allows the user to integrate their own tools with their own logic easily.
• Logging and tracing integrated: using phoenix, the open source tracing and logging tool for LLMs. This provides the user with a detailed traceability of the agents and their execution.
• Multi-Model Support: more than 300 supported and empowered by LiteLLM. The most popular providers:
• Anthropic: Claude 3.7, Claude 3.5, Claude 3, Claude 3 Opus
• OpenAI: O1, O1 Mini, O3 Mini, GPT-4o, GPT-4.5 Preview
• DeepSeek: DeepSeek V3, DeepSeek R1
• Ollama: Qwen2.5 72B, Qwen2.5 14B, etc

Closed-source alternatives

Cybersecurity AI is a critical field, yet many groups are misguidedly pursuing it through closed-source methods for pure economic return, leveraging similar techniques and building upon existing closed-source (often third-party owned) models. This approach not only squanders valuable engineering resources but also represents an economic waste and results in redundant efforts, as they often end up reinventing the wheel. Here are some of the closed-source initiatives we keep track of and attempting to leverage genAI and agentic frameworks in cybersecurity AI:

• Autonomous Cyber
• CrackenAGI
• ETHIACK
• Horizon3
• Irregular
• Kindo
• Lakera
• Mindfort
• Mindgard
• NDAY Security
• Penligent
• Runsybil
• Selfhack
• Sola Security
• SQUR
• Staris
• Sxipher (seems discontinued)
• Terra Security
• Vibeproxy
• Xint
• XBOW
• ZeroPath
• Zynap
• 7ai

Learn - CAI Fluency

[!NOTE]

CAI Fluency technical report (arXiv:2508.13588) establishes formal educational frameworks for cybersecurity AI literacy.

	Description	English	Spanish
Episode 0: What is CAI?	Cybersecurity AI (CAI) explained
Episode 1: The CAI Framework	Vision & Ethics - Explore the core motivation behind CAI and delve into the crucial ethical principles guiding its development. Understand the motivation behind CAI and how you can actively contribute to the future of cybersecurity and the CAI framework.
Episode 2: From Zero to Cyber Hero	Breaking into Cybersecurity with AI - A comprehensive guide for complete beginners to become cybersecurity practitioners using CAI and AI tools. Learn how to leverage artificial intelligence to accelerate your cybersecurity learning journey, from understanding basic security concepts to performing real-world security assessments, all without requiring prior cybersecurity experience.
Episode 3: Vibe-Hacking Tutorial	"My first Hack" - A Vibe-Hacking guide for newbies. We demonstrate a simple web security hack using a default agent and show how to leverage tools and interpret CAI output with the help of the CAI Python API. You'll also learn to compare different LLM models to find the best fit for your hacking endeavors.
Episode 4: Intro ReAct	The Evolution of LLMs - Learn how LLMs evolved from basic language models to advanced multiagency AI systems. From basic LLMs to Chain-of-Thought and Reasoning LLMs towards ReAct and Multi-Agent Architectures. Get to know the basic terms
Episode 5: CAI on CTF challenges	Dive into Capture The Flag (CTF) competitions using CAI. Learn how to leverage AI agents to solve various cybersecurity challenges including web exploitation, cryptography, reverse engineering, and forensics. Discover how to configure CAI for competitive hacking scenarios and maximize your CTF performance with intelligent automation.
Annex 1: CAI 0.5.x release	Introduce version 0.5 of CAI including new multi-agent functionality, new commands such as /history, /compact, /graph or /memory and a case study showing how CAI found a critical security flaw in OT heap pumps spread around the world.
Annex 2: CAI 0.4.x release and alias0	Introducing version 0.4 of CAI with streaming and improved MCP support. We also introduce alias0, the Privacy-First Cybersecurity AI, a Model-of-Models Intelligence that implements a Privacy-by-Design architecture and obtains state-of-the-art results in cybersecurity benchmarks.
Annex 3: Cybersecurity AI Community Meeting #1	First Cybersecurity AI (CAI) community meeting, over 40 participants from academia, industry, and defense gathered to discuss the open-source scaffolding behind CAI — a project designed to build agentic AI systems for cybersecurity that are open, modular, and Bug Bounty-ready.
Annex 4: CAI PRO PoC	Short proof-of-concept demonstration of CAI PRO capabilities showcasing the Professional Edition with unlimited alias1 tokens, unrestricted AI, and enterprise-grade security testing features.
Annex 5: CAI PoC	Short proof-of-concept demonstration of CAI Community Edition showcasing the open-source framework's core capabilities for AI-powered security testing and vulnerability discovery.
Annex 6: CAI in Jaula del N00B	CAI (CIBERSEGURIDAD CON IA) LUIJAIT EN LA JAULA DEL N00B - Demonstration and discussion of CAI framework capabilities in the popular Spanish cybersecurity podcast/show.

:nut_and_bolt: Install

[!NOTE] CAI Professional Edition Users: If you have an active CAI Pro subscription, we provide dedicated installation guides for versions 0.5 and 0.6. Official support is available for Ubuntu 24.04 (x86_64). Installation instructions for other operating systems are provided as-is without official support:

• CAI Pro v0.6 Installation Guide
• CAI Pro v0.5 Installation Guide

Community Edition Installation

pip install cai-framework

Always create a new virtual environment to ensure proper dependency installation when updating CAI.

The following subsections provide a more detailed walkthrough on selected popular Operating Systems. Refer to the Development section for developer-related install instructions. For API Keys env syntax check litellm Documentation. LiteLLM Documentation

OS X

brew update && \
    brew install git [email protected]

# Create virtual environment
python3.12 -m venv cai_env

# Install the package from the local directory
source cai_env/bin/activate && pip install cai-framework

# Generate a .env file and set up with defaults
echo -e 'OPENAI_API_KEY="sk-1234"\nANTHROPIC_API_KEY=""\nOLLAMA=""\nPROMPT_TOOLKIT_NO_CPR=1\nCAI_STREAM=false' > .env

# Launch CAI
cai  # first launch it can take up to 30 seconds

Ubuntu 24.04

sudo apt-get update && \
    sudo apt-get install -y git python3-pip python3.12-venv

# Create the virtual environment
python3.12 -m venv cai_env

# Install the package from the local directory
source cai_env/bin/activate && pip install cai-framework

# Generate a .env file and set up with defaults
echo -e 'OPENAI_API_KEY="sk-1234"\nANTHROPIC_API_KEY=""\nOLLAMA=""\nPROMPT_TOOLKIT_NO_CPR=1\nCAI_STREAM=false' > .env

# Launch CAI
cai  # first launch it can take up to 30 seconds

Ubuntu 20.04

sudo apt-get update && \
    sudo apt-get install -y software-properties-common

# Fetch Python 3.12
sudo add-apt-repository ppa:deadsnakes/ppa && sudo apt update
sudo apt install python3.12 python3.12-venv python3.12-dev -y

# Create the virtual environment
python3.12 -m venv cai_env

# Install the package from the local directory
source cai_env/bin/activate && pip install cai-framework

# Generate a .env file and set up with defaults
echo -e 'OPENAI_API_KEY="sk-1234"\nANTHROPIC_API_KEY=""\nOLLAMA=""\nPROMPT_TOOLKIT_NO_CPR=1\nCAI_STREAM=false' > .env

# Launch CAI
cai  # first launch it can take up to 30 seconds

Windows WSL

Go to the Microsoft page: https://learn.microsoft.com/en-us/windows/wsl/install. Here you will find all the instructions to install WSL

From Powershell write: wsl --install

sudo apt-get update && \
    sudo apt-get install -y git python3-pip python3-venv

# Create the virtual environment
python3 -m venv cai_env

# Install the package from the local directory
source cai_env/bin/activate && pip install cai-framework

# Generate a .env file and set up with defaults. If Ollama runs on your windows host, wsl needs to use your host IP for it to become reachable
echo -e 'OPENAI_API_KEY="sk-1234"\nANTHROPIC_API_KEY=""\nOLLAMA=""\nOLLAMA_API_BASE="http://Your.Host.Ip.Here:11434"\nPROMPT_TOOLKIT_NO_CPR=1\nCAI_STREAM=false' > .env

# Launch CAI
cai  # first launch it can take up to 30 seconds

You might run into issues running cai on ubuntu since some agents assume they are running on a Kali Instance and are not able to find the tools needed. So as an alternative you can use the docker compose file in the dockerized folder instead. This also works from within wsl if docker is installed. in that case fetch the dockerized folder (no need for the whole repo) and run from within it. For API Keys env syntax check litellm Documentation. LiteLLM Documentation

#build and run docker compose Build takes around 20 min.
docker compose build && docker compose up -d

#access cai
docker compose exec cai cai

Android

We recommend having at least 8 GB of RAM:

1. First of all, install userland https://play.google.com/store/apps/details?id=tech.ula&hl=es

2. Install Kali minimal in basic options (for free). [Or any other kali option if preferred]

3. Update apt keys like in this example: https://superuser.com/questions/1644520/apt-get-update-issue-in-kali, inside UserLand's Kali terminal execute

# Get new apt keys
wget http://http.kali.org/kali/pool/main/k/kali-archive-keyring/kali-archive-keyring_2024.1_all.deb

# Install new apt keys
sudo dpkg -i kali-archive-keyring_2024.1_all.deb && rm kali-archive-keyring_2024.1_all.deb

# Update APT repository
sudo apt-get update

# CAI requieres python 3.12, lets install it (CAI for kali in Android)
sudo apt-get update && sudo apt-get install -y git python3-pip build-essential zlib1g-dev libncurses5-dev libgdbm-dev libnss3-dev libssl-dev libreadline-dev libffi-dev libsqlite3-dev wget libbz2-dev pkg-config
wget https://www.python.org/ftp/python/3.12.4/Python-3.12.4.tar.xz
tar xf Python-3.12.4.tar.xz
cd ./configure --enable-optimizations
sudo make altinstall # This command takes long to execute

# Clone CAI's source code
git clone https://github.com/aliasrobotics/cai && cd cai

# Create virtual environment
python3.12 -m venv cai_env

# Install the package from the local directory
source cai_env/bin/activate && pip3 install -e .

# Generate a .env file and set up
cp .env.example .env  # edit here your keys/models

# Launch CAI
cai

:nut_and_bolt: Setup .env file

CAI leverages the .env file to load configuration at launch. To facilitate the setup, the repo provides an exemplary .env.example file provides a template for configuring CAI's setup and your LLM API keys to work with desired LLM models.

:warning: Important:

CAI does NOT provide API keys for any model by default. Don't ask us to provide keys, use your own or host your own models.

:warning: Note:

The OPENAI_API_KEY must not be left blank. It should contain either "sk-123" (as a placeholder) or your actual API key. See https://github.com/aliasrobotics/cai/issues/27.

:warning: Note:

If you are using alias1 model, make sure that CAI is >0.4.0 version and here you have an .env example to be able to use it.

OPENAI_API_KEY="sk-1234"
OLLAMA=""
ALIAS_API_KEY="<sk-your-key>"  # note, add yours
CAI_STREAM=False
CAI_MODEL="alias1"

🔹 Custom OpenAI Base URL Support

CAI supports configuring a custom OpenAI API base URL via the OPENAI_BASE_URL environment variable. This allows users to redirect API calls to a custom endpoint, such as a proxy or self-hosted OpenAI-compatible service.

Example .env entry configuration:

OLLAMA_API_BASE="https://custom-openai-proxy.com/v1"

Or directly from the command line:

OLLAMA_API_BASE="https://custom-openai-proxy.com/v1" cai

:triangular_ruler: Architecture:

CAI focuses on making cybersecurity agent coordination and execution lightweight, highly controllable, and useful for humans. To do so it builds upon 8 pillars: Agents, Tools, Handoffs, Patterns, Turns, Tracing, Guardrails and HITL.

                  ┌───────────────┐           ┌───────────┐
                  │      HITL     │◀─────-───▶│   Turns   │
                  └───────┬───────┘           └───────────┘
                          │
                          ▼
┌───────────┐       ┌───────────┐       ┌───────────┐      ┌───────────┐
│  Patterns │◀──-──▶│  Handoffs │◀──-─▶ │   Agents  │◀──-─▶│    LLMs   │
└───────────┘       └─────┬─────┘       └─────┬─────┘      └───────────┘
                          │                   │
                          │                   ▼
┌────────────┐       ┌────┴──────┐       ┌───────────┐     ┌────────────┐
│ Extensions │◀────▶ │  Tracing  │       │   Tools   │◀──▶ │ Guardrails │
└────────────┘       └───────────┘       └───────────┘     └────────────┘
                                              │
                          ┌─────────────┬─────┴────┬─────────────┐
                          ▼             ▼          ▼             ▼
                    ┌───────────┐┌───────────┐┌────────────┐┌───────────┐
                    │ LinuxCmd  ││ WebSearch ││    Code    ││ SSHTunnel │
                    └───────────┘└───────────┘└────────────┘└───────────┘

If you want to dive deeper into the code, check the following files as a start point for using CAI:

• init.py
• cli.py - entrypoint for command line interface
• util.py - utility functions
• agents - Agent implementations
• internal - CAI internal functions (endpoints, metrics, logging, etc.)
• prompts - Agent Prompt Database
• repl - CLI aesthetics and commands
• sdk - CAI command sdk
• tools - agent tools

🔹 Agent

At its core, CAI abstracts its cybersecurity behavior via Agents and agentic Patterns. An Agent in an intelligent system that interacts with some environment. More technically, within CAI we embrace a robotics-centric definition wherein an agent is anything that can be viewed as a system perceiving its environment through sensors, reasoning about its goals and and acting accordingly upon that environment through actuators (adapted from Russel & Norvig, AI: A Modern Approach). In cybersecurity, an Agent interacts with systems and networks, using peripherals and network interfaces as sensors, reasons accordingly and then executes network actions as if actuators. Correspondingly, in CAI, Agents implement the ReACT (Reasoning and Action) agent model². For more information, see the example here for the full execution code, and refer to this jupyter notebook for a tutorial on how to use it.

from cai.sdk.agents import Agent, Runner, OpenAIChatCompletionsModel

import os
from openai import AsyncOpenAI
from dotenv import load_dotenv
load_dotenv()

agent = Agent(
      name="Custom Agent",
      instructions="""You are a Cybersecurity expert Leader""",
      model=OpenAIChatCompletionsModel(
          model=os.getenv('CAI_MODEL', "openai/gpt-4o"),
          openai_client=AsyncOpenAI(),
          )
      )

message = "Tell me about recursion in programming."
result = await Runner.run(agent, message)

🔹 Tools

Tools let cybersecurity agents take actions by providing interfaces to execute system commands, run security scans, analyze vulnerabilities, and interact with target systems and APIs - they are the core capabilities that enable CAI agents to perform security tasks effectively; in CAI, tools include built-in cybersecurity utilities (like LinuxCmd for command execution, WebSearch for OSINT gathering, Code for dynamic script execution, and SSHTunnel for secure remote access), function calling mechanisms that allow integration of any Python function as a security tool, and agent-as-tool functionality that enables specialized security agents (such as reconnaissance or exploit agents) to be used by other agents, creating powerful collaborative security workflows without requiring formal handoffs between agents. For more information, please refer to the example here for the complete configuration of custom functions.

from cai.sdk.agents import Agent, Runner, OpenAIChatCompletionsModel
from cai.tools.reconnaissance.exec_code import execute_code
from cai.tools.reconnaissance.generic_linux_command import generic_linux_command

import os
from openai import AsyncOpenAI
from dotenv import load_dotenv
load_dotenv()

agent = Agent(
      name="Custom Agent",
      instructions="""You are a Cybersecurity expert Leader""",
      tools= [
        generic_linux_command,
        execute_code
      ],
      model=OpenAIChatCompletionsModel(
          model=os.getenv('CAI_MODEL', "openai/gpt-4o"),
          openai_client=AsyncOpenAI(),
          )
      )

message = "Tell me about recursion in programming."
result = await Runner.run(agent, message)

You may find different tools. They are grouped in 6 major categories inspired by the security kill chain ³:

1. Reconnaissance and weaponization - reconnaissance (crypto, listing, etc)
2. Exploitation - exploitation
3. Privilege escalation - escalation
4. Lateral movement - lateral
5. Data exfiltration - exfiltration
6. Command and control - control

🔹 Handoffs

Handoffs allow an Agent to delegate tasks to another agent, which is crucial in cybersecurity operations where specialized expertise is needed for different phases of an engagement. In our framework, Handoffs are implemented as tools for the LLM, where a handoff/transfer function like transfer_to_flag_discriminator enables the ctf_agent to pass control to the flag_discriminator_agent once it believes it has found the flag. This creates a security validation chain where the first agent handles exploitation and flag discovery, while the second agent specializes in flag verification, ensuring proper segregation of duties and leveraging specialized capabilities of different models for distinct security tasks. For more information, please refer to the example here for the full execution code.

from cai.sdk.agents import function_tool
from cai.tools.common import run_command
from cai.sdk.agents import Agent, OpenAIChatCompletionsModel, HandoffInputData, Runner, function_tool, handoff, trace
from cai.sdk.agents.extensions import handoff_filters

import os
from openai import AsyncOpenAI
from dotenv import load_dotenv
load_dotenv()

@function_tool
def execute_cli_command(command: str) -> str:
    return run_command(command)

flag_discriminator = Agent(
    name="Flag discriminator",
    description="Agent focused on extracting the flag from the output",
    instructions="You are an agent tailored to extract the flag from a given output.",
    model=OpenAIChatCompletionsModel(
        model=os.getenv('CAI_MODEL', "qwen2.5:14b"),
        openai_client=AsyncOpenAI(),
    ) 
)

ctf_agent = Agent(
    name="CTF agent",
    description="Agent focused on conquering security challenges",
    instructions="You are a Cybersecurity expert Leader facing a CTF",
    tools=[
        execute_cli_command,
    ],
    model=OpenAIChatCompletionsModel(
        model= os.getenv('CAI_MODEL', "qwen2.5:14b"),
        openai_client=AsyncOpenAI(),
    ), 
    handoffs = [flag_discriminator]
)

🔹 Patterns

An agentic Pattern is a structured design paradigm in artificial intelligence systems where autonomous or semi-autonomous agents operate within a defined interaction framework (the pattern) to achieve a goal. These Patterns specify the organization, coordination, and communication methods among agents, guiding decision-making, task execution, and delegation.

An agentic pattern (AP) can be formally defined as a tuple:

\[ AP = (A, H, D, C, E) \]

wherein:

• \(A\) (Agents): A set of autonomous entities, \( A = \{a_1, a_2, ..., a_n\} \), each with defined roles, capabilities, and internal states.
• \(H\) (Handoffs): A function \( H: A \times T \to A \) that governs how tasks \( T \) are transferred between agents based on predefined logic (e.g., rules, negotiation, bidding).
• \(D\) (Decision Mechanism): A decision function \( D: S \to A \) where \( S \) represents system states, and \( D \) determines which agent takes action at any given time.
• \(C\) (Communication Protocol): A messaging function \( C: A \times A \to M \), where \( M \) is a message space, defining how agents share information.
• \(E\) (Execution Model): A function \( E: A \times I \to O \) where \( I \) is the input space and \( O \) is the output space, defining how agents perform tasks.

When building Patterns, we generall y classify them among one of the following categories, though others exist:

For more information and examples of common agentic patterns, see the examples folder.

🔹 Turns and Interactions

During the agentic flow (conversation), we distinguish between interactions and turns.

• Interactions are sequential exchanges between one or multiple agents. Each agent executing its logic corresponds with one interaction. Since an Agent in CAI generally implements the ReACT agent model², each interaction consists of 1) a reasoning step via an LLM inference and 2) act by calling zero-to-n Tools. This is defined inprocess_interaction() in core.py.
• Turns: A turn represents a cycle of one ore more interactions which finishes when the Agent (or Pattern) executing returns None, judging there're no further actions to undertake. This is defined in run(), see core.py.

[!NOTE] CAI Agents are not related to Assistants in the Assistants API. They are named similarly for convenience, but are otherwise completely unrelated. CAI is entirely powered by the Chat Completions API and is hence stateless between calls.

🔹 Tracing

CAI implements AI observability by adopting the OpenTelemetry standard and to do so, it leverages Phoenix which provides comprehensive tracing capabilities through OpenTelemetry-based instrumentation, allowing you to monitor and analyze your security operations in real-time. This integration enables detailed visibility into agent interactions, tool usage, and attack vectors throughout penetration testing workflows, making it easier to debug complex exploitation chains, track vulnerability discovery processes, and optimize agent performance for more effective security assessments.

🔹 Guardrails

Guardrails provide a critical security layer for CAI agents, protecting against prompt injection attacks and preventing execution of dangerous commands. These guardrails run in parallel to agents, validating both input and output to ensure safe operation. The framework includes:

• Input Guardrails: Detect and block prompt injection attempts before they reach agents, using pattern matching, Unicode homograph detection, and AI-powered analysis
• Output Guardrails: Validate agent outputs before execution, preventing dangerous commands like reverse shells, fork bombs, or data exfiltration
• Multi-layered Defense: Protection at input, processing, and execution stages with tool-level validation
• Base64/Base32 Aware: Automatically decodes and analyzes encoded payloads to detect hidden malicious commands
• Configurable: Can be enabled/disabled via CAI_GUARDRAILS environment variable

For detailed implementation, see docs/guardrails.md and docs/cai_prompt_injection.md.

🔹 Human-In-The-Loop (HITL)

                      ┌─────────────────────────────────┐
                      │                                 │
                      │      Cybersecurity AI (CAI)     │
                      │                                 │
                      │       ┌─────────────────┐       │
                      │       │  Autonomous AI  │       │
                      │       └────────┬────────┘       │
                      │                │                │
                      │                │                │
                      │       ┌────────▼─────────┐      │
                      │       │ HITL Interaction │      │
                      │       └────────┬─────────┘      │
                      │                │                │
                      └────────────────┼────────────────┘
                                       │
                                       │ Ctrl+C (cli.py)
                                       │
                           ┌───────────▼───────────┐
                           │   Human Operator(s)   │
                           │  Expertise | Judgment │
                           │    Teleoperation      │
                           └───────────────────────┘

CAI delivers a framework for building Cybersecurity AIs with a strong emphasis on semi-autonomous operation, as the reality is that fully-autonomous cybersecurity systems remain premature and face significant challenges when tackling complex tasks. While CAI explores autonomous capabilities, we recognize that effective security operations still require human teleoperation providing expertise, judgment, and oversight in the security process.

Accordingly, the Human-In-The-Loop (HITL) module is a core design principle of CAI, acknowledging that human intervention and teleoperation are essential components of responsible security testing. Through the cli.py interface, users can seamlessly interact with agents at any point during execution by simply pressing Ctrl+C. This is implemented across core.py and also in the REPL abstractions REPL.

:rocket: Quickstart

To start CAI after installing it, just type cai in the CLI:

└─# cai

          CCCCCCCCCCCCC      ++++++++   ++++++++      IIIIIIIIII
       CCC::::::::::::C  ++++++++++       ++++++++++  I::::::::I
     CC:::::::::::::::C ++++++++++         ++++++++++ I::::::::I
    C:::::CCCCCCCC::::C +++++++++    ++     +++++++++ II::::::II
   C:::::C       CCCCCC +++++++     +++++     +++++++   I::::I
  C:::::C                +++++     +++++++     +++++    I::::I
  C:::::C                ++++                   ++++    I::::I
  C:::::C                 ++                     ++     I::::I
  C:::::C                  +   +++++++++++++++   +      I::::I
  C:::::C                    +++++++++++++++++++        I::::I
  C:::::C                     +++++++++++++++++         I::::I
   C:::::C       CCCCCC        +++++++++++++++          I::::I
    C:::::CCCCCCCC::::C         +++++++++++++         II::::::II
     CC:::::::::::::::C           +++++++++           I::::::::I
       CCC::::::::::::C             +++++             I::::::::I
          CCCCCCCCCCCCC               ++              IIIIIIIIII

                      Cybersecurity AI (CAI), vX.Y.Z
                          Bug bounty-ready AI

CAI>

That should initialize CAI and provide a prompt to execute any security task you want to perform. The navigation bar at the bottom displays important system information. This information helps you understand your environment while working with CAI.

Here's a quick demo video to help you get started with CAI. We'll walk through the basic steps — from launching the tool to running your first AI-powered task in the terminal. Whether you're a beginner or just curious, this guide will show you how easy it is to begin using CAI.

From here on, type on CAI and start your security exercise. Best way to learn is by example:

Environment Variables

For using private models, you are given a .env.example file. Copy it and rename it as .env. Fill in your corresponding API keys, and you are ready to use CAI.

List of Environment Variables

OpenRouter Integration

The Cybersecurity AI (CAI) platform offers seamless integration with OpenRouter, a unified interface for Large Language Models (LLMs). This integration is crucial for users who wish to leverage advanced AI capabilities in their cybersecurity tasks. OpenRouter acts as a bridge, allowing CAI to communicate with various LLMs, thereby enhancing the flexibility and power of the AI agents used within CAI.

To enable OpenRouter support in CAI, you need to configure your environment by adding specific entries to your .env file. This setup ensures that CAI can interact with the OpenRouter API, facilitating the use of sophisticated models like Meta-LLaMA. Here’s how you can configure it:

CAI_AGENT_TYPE=redteam_agent
CAI_MODEL=openrouter/meta-llama/llama-4-maverick
OPENROUTER_API_KEY=<sk-your-key>  # note, add yours
OPENROUTER_API_BASE=https://openrouter.ai/api/v1

Azure OpenAI

The Cybersecurity AI (CAI) platform integrates seamlessly with Azure OpenAI, enabling organizations to run CAI against enterprise-hosted models (e.g., gpt-4o). This pathway is ideal for teams that must operate within Azure governance while leveraging advanced model capabilities. To enable Azure OpenAI support in CAI, configure your environment by adding the following entries to your .env. This ensures CAI can reach your Azure deployment endpoint and authenticate correctly.

CAI_AGENT_TYPE=redteam_agent
CAI_MODEL=azure/<model-name-deployed>
# Required: keep non-empty even when using Azure
OPENAI_API_KEY=dummy
# Azure credentials and endpoint
AZURE_API_KEY=<your-azure-openai-key>
AZURE_API_BASE=https://<resource>.openai.azure.com/openai/deployments/<deployment-name>/chat/completions?api-version=2025-01-01-preview

MCP

CAI supports the Model Context Protocol (MCP) for integrating external tools and services with AI agents. MCP is supported via two transport mechanisms:

1. SSE (Server-Sent Events) - For web-based servers that push updates over HTTP connections:

CAI>/mcp load http://localhost:9876/sse burp

2. STDIO (Standard Input/Output) - For local inter-process communication:

CAI>/mcp load stdio myserver python mcp_server.py

Once connected, you can add the MCP tools to any agent:

CAI>/mcp add burp redteam_agent
Adding tools from MCP server 'burp' to agent 'Red Team Agent'...
                                 Adding tools to Red Team Agent
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ Tool                              ┃ Status ┃ Details                                         ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ send_http_request                 │ Added  │ Available as: send_http_request                 │
│ create_repeater_tab               │ Added  │ Available as: create_repeater_tab               │
│ send_to_intruder                  │ Added  │ Available as: send_to_intruder                  │
│ url_encode                        │ Added  │ Available as: url_encode                        │
│ url_decode                        │ Added  │ Available as: url_decode                        │
│ base64encode                      │ Added  │ Available as: base64encode                      │
│ base64decode                      │ Added  │ Available as: base64decode                      │
│ generate_random_string            │ Added  │ Available as: generate_random_string            │
│ output_project_options            │ Added  │ Available as: output_project_options            │
│ output_user_options               │ Added  │ Available as: output_user_options               │
│ set_project_options               │ Added  │ Available as: set_project_options               │
│ set_user_options                  │ Added  │ Available as: set_user_options                  │
│ get_proxy_http_history            │ Added  │ Available as: get_proxy_http_history            │
│ get_proxy_http_history_regex      │ Added  │ Available as: get_proxy_http_history_regex      │
│ get_proxy_websocket_history       │ Added  │ Available as: get_proxy_websocket_history       │
│ get_proxy_websocket_history_regex │ Added  │ Available as: get_proxy_websocket_history_regex │
│ set_task_execution_engine_state   │ Added  │ Available as: set_task_execution_engine_state   │
│ set_proxy_intercept_state         │ Added  │ Available as: set_proxy_intercept_state         │
│ get_active_editor_contents        │ Added  │ Available as: get_active_editor_contents        │
│ set_active_editor_contents        │ Added  │ Available as: set_active_editor_contents        │
└───────────────────────────────────┴────────┴─────────────────────────────────────────────────┘
Added 20 tools from server 'burp' to agent 'Red Team Agent'.
CAI>/agent 13
CAI>Create a repeater tab

You can list all active MCP connections and their transport types:

CAI>/mcp list

https://github.com/user-attachments/assets/386a1fd3-3469-4f84-9396-2a5236febe1f

Development

Development is facilitated via VS Code dev. environments. To try out our development environment, clone the repository, open VS Code and enter de dev. container mode:

Contributions

If you want to contribute to this project, use Pre-commit before your MR

pip install pre-commit
pre-commit # files staged
pre-commit run --all-files # all files

Optional Requirements: caiextensions

Currently, the extensions are not publicly available as the engineering endeavour to maintain them is significant. Instead, we're making selected custom caiextensions available for partner companies across collaborations.

:information_source: Usage Data Collection

CAI is provided free of charge for researchers. To improve CAI’s detection accuracy, advance open security research, and develop and train future models, we ask you to contribute to the CAI community by allowing usage data collection. This data helps us identify areas for improvement, understand how the framework is being used, prioritize new features, and support model training and evaluation efforts.

The legal basis for data collection is under Art. 6 (1)(f) GDPR — CAI’s legitimate interest in maintaining, improving, and advancing security tooling and research — with Art. 89 safeguards applied for research purposes.

The collected data includes:

• Basic system information (OS type, Python version)
• Username and IP information
• Tool usage patterns and performance metrics
• Model interactions and token usage statistics

We take your privacy seriously and only collect what is necessary to improve CAI, support research, and train and evaluate models responsibly. For further information, contact research＠aliasrobotics.com. You can disable some data collection features via the CAI_TELEMETRY environment variable, although we encourage you to keep it enabled to contribute to ongoing research and model development:

CAI_TELEMETRY=False cai

Reproduce CI-Setup locally

To simulate the CI/CD pipeline, you can run the following in the Gitlab runner machines:

docker run --rm -it \
  --privileged \
  --network=exploitflow_net \
  --add-host="host.docker.internal:host-gateway" \
  -v /cache:/cache \
  -v /var/run/docker.sock:/var/run/docker.sock:rw \
  registry.gitlab.com/aliasrobotics/alias_research/cai:latest bash

FAQ

OLLAMA is giving me 404 errors

Ollama's API in OpenAI mode uses /v1/chat/completions whereas the openai library uses base_url + /chat/completions.

We adopt the latter for overall alignment with the gen AI community and empower the former by allowing users to add the v1 themselves via:

OLLAMA_API_BASE=http://IP:PORT/v1

See the following issues that treat this topic in more detail:

• https://github.com/aliasrobotics/cai/issues/76
• https://github.com/aliasrobotics/cai/issues/83
• https://github.com/aliasrobotics/cai/issues/82

Where are all the caiextensions?

See all caiextensions

How do I install the report caiextension?

See here

How do I set up SSH access for Gitlab?

Generate a new SSH key

ssh-keygen -t ed25519

Add the key to the SSH agent

ssh-add ~/.ssh/id_ed25519

Add the public key to Gitlab Copy the key and add it to Gitlab under https://gitlab.com/-/user_settings/ssh_keys

cat ~/.ssh/id_ed25519.pub

To verify it:

ssh -T [email protected]
Welcome to GitLab, @vmayoral!

How do I clear Python cache?

find . -name "*.pyc" -delete && find . -name "__pycache__" -delete

If host networking is not working with ollama check whether it has been disabled in Docker because you are not signed in

Docker in OS X behaves funny sometimes. Check if the following message has shown up:

Host networking has been disabled because you are not signed in. Please sign in to enable it.

Make sure this has been addressed and also that the Dev Container is not forwarding the 8000 port (click on x, if necessary in the ports section).

To verify connection, from within the VSCode devcontainer:

curl -v http://host.docker.internal:8000/api/version

Run CAI against any target

The starting user prompt in this case is: Target IP: 192.168.3.10, perform a full network scan.

The agent started performing a nmap scan. You could either interact with the agent and give it more instructions, or let it run to see what it explores next.

How do I interact with the agent? Type twice CTRL + C

If you want to use the HITL mode, you can do it by presssing twice Ctrl + C. This will allow you to interact (prompt) with the agent whenever you want. The agent will not lose the previous context, as it is stored in the history variable, which is passed to it and any agent that is called. This enables any agent to use the previous information and be more accurate and efficient.

Can I change the model while CAI is running? /model

Use /model to change the model.

How can I list all the agents available? /agent

Use /agent to list all the agents available.

Where can I list all the environment variables? /env

How can I monitor token usage and costs?

Use /cost in the REPL for session spend and token statistics, /compact when conversations grow long, and (in TUI mode) the per-terminal cost and model indicators in the UI.

CAI> /cost

See the CLI commands reference for the full command list.

How to know more about the CLI? /help

How can I trace the whole execution? The environment variable CAI_TRACING allows the user to set it to CAI_TRACING=true to enable tracing, or CAI_TRACING=false to disable it. When CAI is prompted by the first time, the user is provided with two paths, the execution log, and the tracing log.

Can I expand CAI capabilities using previous run logs?

Yes. Today CAI performs best by relying on In‑Context Learning (ICL). Rather than building long‑term stores, the recommended workflow is to load relevant prior logs directly into the current session so the model can reason with them in context.

Use the /load command to bring JSONL logs into CAI’s context (this replaces the legacy memory-loading tool):

CAI>/load logs/cai_20250408_111856.jsonl         # Load into current agent
CAI>/load <file> agent <name>                    # Load into a specific agent
CAI>/load <file> all                             # Distribute across all agents
CAI>/load <file> parallel                        # Match to configured parallel agents
# Tip: if you omit <file>, /load uses `logs/last`. Alias: /l

CAI prints the path to the current run’s JSONL log at startup (highlighted in orange), which you can pass to /load:

Legacy notes: earlier “memory extension” mechanisms (episodic/semantic stores and offline ingestion) are retained for reference only. See src/cai/agents/memory.py for background and legacy details. Our current direction prioritizes ICL over persistent memory.

Can I expand CAI capabilities using scripts or extra information?

Currently, CAI supports text based information. You can add any extra information on the target you are facing by copy-pasting it directly into the system or user prompt.

How? By adding it to the system (system_master_template.md) or the user prompt (user_master_template.md). You can always directly prompt the path to the model, and it will cat it.

How CAI licence works?

CAI’s current license does not restrict usage for research purposes. You are free to use CAI for security assessments (pentests), to develop additional features, and to integrate it into your research activities, as long as you comply with local laws.

If you or your organization start benefiting commercially from CAI (e.g., offering pentesting services powered by CAI), then a commercial license will be required to help sustain the project.

CAI itself is not a profit-seeking initiative. Our goal is to build a sustainable open-source project. We simply ask that those who profit from CAI contribute back and support our ongoing development.

I get a Unable to locate package python3.12-venv when installing the prerequisites on my debian based system!

The easiest way to get around this is to simply install python3.12 from source.

Citation

If you want to cite our work, please use the following (ordered by publication date):

@article{mayoral2025cai,
  title={CAI: An Open, Bug Bounty-Ready Cybersecurity AI},
  author={Mayoral-Vilches, V{\'\i}ctor and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a and Espejo, Lidia Salas and Crespo-{\'A}lvarez, Marti{\~n}o and Oca-Gonzalez, Francisco and Balassone, Francesco and Glera-Pic{\'o}n, Alfonso and Ayucar-Carbajo, Unai and Ruiz-Alcalde, Jon Ander and Rass, Stefan and Pinzger, Martin and Gil-Uriarte, Endika},
  journal={arXiv preprint arXiv:2504.06017},
  year={2025}
}

@article{mayoral2025automation,
  title={Cybersecurity AI: The Dangerous Gap Between Automation and Autonomy},
  author={Mayoral-Vilches, V{\'\i}ctor},
  journal={arXiv preprint arXiv:2506.23592},
  year={2025}
}

@article{mayoral2025fluency,
  title={CAI Fluency: A Framework for Cybersecurity AI Fluency},
  author={Mayoral-Vilches, V{\'\i}ctor and Wachter, Jasmin and Chavez, Crist{\'o}bal RJ and Schachner, Cathrin and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a},
  journal={arXiv preprint arXiv:2508.13588},
  year={2025}
}

@article{mayoral2025hacking,
  title={Cybersecurity AI: Hacking the AI Hackers via Prompt Injection},
  author={Mayoral-Vilches, V{\'\i}ctor and Rynning, Per Mannermaa},
  journal={arXiv preprint arXiv:2508.21669},
  year={2025}
}

@article{mayoral2025humanoid,
  title={Cybersecurity AI: Humanoid Robots as Attack Vectors},
  author={Mayoral-Vilches, V{\'\i}ctor},
  journal={arXiv preprint arXiv:2509.14139},
  year={2025}
}

@article{balassone2025evaluation,
  title={Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs},
  author={Balassone, Francesco and Mayoral-Vilches, V{\'\i}ctor and Rass, Stefan and Pinzger, Martin and Perrone, Gaetano and Romano, Simon Pietro and Schartner, Peter},
  journal={arXiv preprint arXiv:2510.17521},
  year={2025}
}

@article{mayoral2025caibench,
  title={CAIBench: A Meta-Benchmark for Evaluating Cybersecurity AI Agents},
  author={Mayoral-Vilches, V{\'\i}ctor and Balassone, Francesco and Navarrete-Lozano, Luis Javier and Sanz-G{\'o}mez, Mar{\'\i}a and Crespo-{\'A}lvarez, Marti{\~n}o and Rass, Stefan and Pinzger, Martin},
  journal={arXiv preprint arXiv:2510.24317},
  year={2025}
}

Acknowledgements

CAI was initially developed by Alias Robotics and co-funded by the European EIC accelerator project RIS (GA 101161136) - HORIZON-EIC-2023-ACCELERATOR-01 call. The original agentic principles are inspired from OpenAI's swarm library and translated into newer prototypes. This project also makes use of other relevant open source building blocks including LiteLLM, and phoenix

Academic Collaborations

CAI benefits from ongoing research collaborations with academic institutions. Researchers interested in collaborative projects, dataset access, or academic licenses should contact [email protected]. We provide special support for:

• PhD research projects
• Academic benchmarking studies
• Security education initiatives
• Open-source contributions from research labs