{"id":24585646,"url":"https://github.com/antoninoLorenzo/AI-OPS","last_synced_at":"2025-10-05T11:31:14.499Z","repository":{"id":243380025,"uuid":"812250737","full_name":"antoninoLorenzo/AI-OPS","owner":"antoninoLorenzo","description":"Penetration Testing AI Assistant","archived":false,"fork":false,"pushed_at":"2024-10-23T22:45:21.000Z","size":5565,"stargazers_count":9,"open_issues_count":0,"forks_count":4,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-24T11:55:06.103Z","etag":null,"topics":["ai-agents","cybersecurity","hacking","hacking-tool","llm","llm-agent","penetration-testing","penetration-testing-framework","penetration-testing-tools","python","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/antoninoLorenzo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-08T11:10:22.000Z","updated_at":"2024-10-23T22:45:24.000Z","dependencies_parsed_at":"2024-06-08T13:42:59.496Z","dependency_job_id":"ecff2000-b31d-4aad-a612-afc5dba1c155","html_url":"https://github.com/antoninoLorenzo/AI-OPS","commit_stats":null,"previous_names":["antoninolorenzo/ai-ops"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/antoninoLorenzo/AI-OPS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/antoninoLorenzo%2FAI-OPS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/antoninoLorenzo%2FAI-OPS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/antoninoLorenzo%2FAI-OPS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/antoninoLorenzo%2FAI-OPS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/antoninoLorenzo","download_url":"https://codeload.github.com/antoninoLorenzo/AI-OPS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/antoninoLorenzo%2FAI-OPS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278445704,"owners_count":25988037,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","cybersecurity","hacking","hacking-tool","llm","llm-agent","penetration-testing","penetration-testing-framework","penetration-testing-tools","python","retrieval-augmented-generation"],"created_at":"2025-01-24T05:14:06.143Z","updated_at":"2025-10-05T11:31:14.493Z","avatar_url":"https://github.com/antoninoLorenzo.png","language":"Python","funding_links":[],"categories":["Python","Pentest \u0026 Red Teaming Agents (131)","📚 Research \u0026 Publications","Pentesting Agents \u0026 Frameworks"],"sub_categories":["🔒 OWASP Top 10 for AI Agents (Non official)","Additional Agents"],"readme":"\u003cdiv align=\"center\"\u003e\n\n  \u003cimg src=\"./static/logo_nobg.png\" style=\"width:100px\" alt=\"AI-OPS-logo\"\u003e\n  \u003ch1\u003eAI-OPS\u003c/h1\u003e\n  \u003cp\u003e\u003cstrong\u003eAI-OPS is a Penetration Testing AI Assistant based on open source LLMs.\u003c/strong\u003e\u003c/p\u003e\n  \n  [![license](https://img.shields.io/badge/LICENSE-MIT-\u003cCOLOR\u003e.svg)](https://shields.io/)\n  ![GitHub last commit (branch)](https://img.shields.io/github/last-commit/antoninoLorenzo/AI-OPS/main)\n  ![pylint](https://img.shields.io/badge/Code%20Quality-8.52-yellow) \n  ![Code Coverage](https://img.shields.io/badge/coverage-61%25-yellow)\n\n\n\u003c/div\u003e\n\n---\n\n### Table of Contents\n\n- [Overview](#overview)\n  - [Key Features](#key-features)\n  - [Supported Models](#supported-models)\n- [Quickstart](#quickstart)\n  - [Requirements](#requirements)\n  - [Get Started](#get-started)\n  - [Additional Information](#additional-information)\n- [⚖️ Ethical and Legal Considerations](#️-ethical-and-legal-considerations)\n  - [Disclaimer](#disclaimer)\n\n\u003e 💡 ***Note:** AI-OPS is currently an experimental project.*\n\n---\n\n## Overview\n\nAI-OPS is a **Penetration Testing AI Assistant** that leverages open-source Large Language Models (*LLMs*)\nto explore the role of Generative AI in ethical hacking. With a focus on accessibility and practical use, it  \naims to accelerate common tasks in pentesting such as exploit development, vulnerability research, and code analysis.\n\n**Disclaimer**: AI-OPS goal is to support human operators rather than automate penetration testing activities entirely,  \nensuring that AI remains a supplementary tool during real-world workflows. As any other automation tool, it doesn't  \nreplace operator competence, neither knowledge: AI won't do the work for you, but it may help in the process.\n\nIn the current iteration, AI-OPS does not  directly interact with target systems. Instead, it serves as an assistive tool that aids in tasks like generating \nproof-of-concept (PoC) exploits, researching security vulnerabilities in specific technologies, and analyzing code for potential flaws.\n\n### Key Features\n\n- 🚀 **Full Open-Source**: There is no reliance on third-party LLM providers; use any model you prefer with [Ollama](https://github.com/ollama/ollama).\n- 🔍 **Web Search**: The AI assistant delivers up-to-date responses by performing online searches via Google.\n\n\u003c!--\n### ▶️ Demo\n\nTODO\n\n--\u003e\n\n### Supported Models\n\nAI-OPS supports virtually any LLM that can be hosted with Ollama, allowing you to tailor the assistant to your  \navailable resources; for detailed setup instructions, see [Configuration](./docs/user/2.Configuration.md).\nWhile flexibility is key, note that performance may vary depending on the model used. Below is a list of currently implemented models.\n\n| Name            | Notes                                                                                              |\n|-----------------|----------------------------------------------------------------------------------------------------|\n| **DeepSeek-r1** | New integration.                                                                                    |\n| **Mistral 7B**  | Using non quantized mistral `mistral:7b-instruct-v0.3-q8_0` gives better results in exploit tasks. |\n| **Gemma2**      | Better compared to mistral in vulnerability research tasks.                                        |\n\n\u003e *Note: AI-OPS prioritizes smaller, efficient LLMs to ensure accessibility and optimal performance, even on limited hardware.*\n\n---\n\n## Quickstart\n\n### Requirements\n\nTo get started with AI-OPS, ensure you have the following dependencies installed:\n\n- **Python** (*\u003e= 3.11*): for AI-OPS CLI interface. \n- **Ollama** (*\u003e= 0.3.0*): for LLM inference.\n- **Docker** : for AI-OPS API.\n\n### Get Started\n\nStart by cloning the repository:\n\n```bash\ngit clone https://github.com/antoninoLorenzo/AI-OPS.git\ncd AI-OPS\n```\n\nThen configure Ollama, you can refer to their [documentation](https://github.com/ollama/ollama/blob/main/docs/README.md) for additional\ndetails:\n\n```bash\nollama run MODEL\n```\n\n\u003e 💡 ***Tip:** If you lack mid/high-end GPUs to run LLMs locally you can follow [my guide](https://github.com/antoninoLorenzo/Ollama-on-Colab-with-ngrok) on how to run Ollama on Google Colab.*\n\nBuild and run the Docker container for the AI-OPS API using the following command. Replace `ENDPOINT` with the URL of your \nOllama instance and `MODEL` with the name of the model you wish to use (e.g., Mistral 7B):\n\n```bash\ndocker build -t ai-ops:api-dev --build-arg ollama_endpoint=ENDPOINT ollama_model=MODEL .\ndocker run -p 8000:8000 ai-ops:api-dev\n```\n\nTo start interacting with AI-OPS, install and run the `ai-ops-cli` command-line client. Make sure to \nreplace `AI-OPS_API_ADDRESS` with the address of your running Docker container (e.g., http://localhost:8000):\n\n```bash\npip install .\nai-ops-cli --api AI-OPS_API_ADDRESS\n```\n\n### Additional Information\n\n**User Documentation**\n\n1. [Usage](./docs/user/1.Usage.md)\n2. [Configuration](./docs/user/2.Configuration.md)\n\n**Developer Documentation**\n\n1. [Project Structure](./docs/development/1.Project%20Structure.md)\n\n---\n\n## ⚖️ Ethical and Legal Considerations\n\n**AI-OPS** is designed as a penetration testing tool intended for academic and educational purposes only. Its primary goal is to assist cybersecurity professionals and enthusiasts in enhancing their understanding and skills in penetration testing through the use of AI-driven automation and tools.\n\n### Disclaimer\n\nThe creators and contributors of **AI-OPS** are not responsible for any misuse of this tool. By using **AI-OPS**, you agree to take full responsibility for your actions and to use the tool in a manner that is ethical, legal, and in accordance with the intended purpose.\n\nThis project is provided \"as-is\" without any warranties, express or implied. The creators are not liable for any damages or legal repercussions resulting from the use of this tool.\n\n\u003e Yes, this section is generated with AI.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FantoninoLorenzo%2FAI-OPS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FantoninoLorenzo%2FAI-OPS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FantoninoLorenzo%2FAI-OPS/lists"}