{"id":49382096,"url":"https://github.com/5GSEC/MobiLLM","last_synced_at":"2026-05-14T17:01:10.082Z","repository":{"id":310839614,"uuid":"1040797729","full_name":"5GSEC/MobiLLM","owner":"5GSEC","description":"Domain-specific LLM for cellular security","archived":false,"fork":false,"pushed_at":"2025-09-16T15:20:29.000Z","size":706,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-12T16:45:15.397Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/5GSEC.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-19T14:18:39.000Z","updated_at":"2025-09-16T15:20:33.000Z","dependencies_parsed_at":"2025-08-30T20:22:37.435Z","dependency_job_id":"87e0cb02-ab7c-44ea-af3a-adf720b2828b","html_url":"https://github.com/5GSEC/MobiLLM","commit_stats":null,"previous_names":["5gsec/mobillm"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/5GSEC/MobiLLM","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/5GSEC%2FMobiLLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/5GSEC%2FMobiLLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/5GSEC%2FMobiLLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/5GSEC%2FMobiLLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/5GSEC","download_url":"https://codeload.github.com/5GSEC/MobiLLM/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/5GSEC%2FMobiLLM/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33034788,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-13T13:14:54.681Z","status":"online","status_checked_at":"2026-05-14T02:00:06.663Z","response_time":57,"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":[],"created_at":"2026-04-28T06:00:28.381Z","updated_at":"2026-05-14T17:01:10.074Z","avatar_url":"https://github.com/5GSEC.png","language":"Python","funding_links":[],"categories":["AI \u0026 Machine Learning"],"sub_categories":["Telecom LLMs \u0026 AI Assistants"],"readme":"# MobiLLM\n\n**Domain-specific LLM for cellular security**\n\nMobiLLM is an intelligent multi-agent system designed specifically for 5G network security analysis and response. It leverages Large Language Models (LLMs) to provide automated threat detection, analysis, and mitigation strategies for cellular networks.\n\n## 🚀 Features\n\n- **Multi-Agent Architecture**: Specialized agents for different security tasks\n- **5G Network Security**: Domain-specific knowledge for cellular security\n- **MITRE ATT\u0026CK Integration**: Maps threats to standard attack frameworks\n- **Automated Response**: Suggests and executes countermeasures\n- **Real-time Analysis**: Processes network events and telemetry data\n- **Human-in-the-Loop**: Approval system for critical actions\n\n## 🏗️ Architecture\n\nMobiLLM uses a multi-agent architecture built with LangGraph:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"mobillm_langgraph.png\" alt=\"MobiLLM LangGraph Architecture\" width=\"350\"/\u003e\n\u003c/p\u003e\n\n### Agent Specializations\n\n- **Chat Agent**: General network queries and service management\n- **Security Analysis Agent**: Threat detection and analysis\n- **Classification Agent**: MITRE ATT\u0026CK technique mapping\n- **Response Planning Agent**: Countermeasure strategy development\n- **Config Tuning Agent**: Network configuration modifications\n\n## 📋 Prerequisites\n\n- Python 3.8+\n- Google Gemini API key\n- Docker (for xApp deployment)\n- Kubernetes cluster (for production deployment)\n\n## 🛠️ Installation\n\n### 1. Clone the Repository\n\n```bash\ngit clone https://github.com/5GSEC/MobiLLM.git\ncd MobiLLM\n```\n\n### 2. Install Dependencies\n\n```bash\npip install -r requirements.txt\n```\n\n### 3. Set Environment Variables\n\n```bash\nexport GOOGLE_API_KEY=\"your_gemini_api_key_here\"\n```\n\n### 4. Verify Installation\n\n```bash\npython -c \"from MobiLLM import MobiLLM_Multiagent; print('Installation successful!')\"\n```\n\n## 🔧 Configuration\n\n### Environment Variables\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `GOOGLE_API_KEY` | Google Gemini API key | Required |\n| `XAPP_ROOT_PATH` | xApp root directory | `./xApp` |\n| `OAI_RAN_CU_CONFIG_PATH` | OAI RAN CU config path | Optional |\n\n### Sample Data\n\nThe system includes sample 5G network data for testing:\n- UE MobiFlow data\n- Base Station MobiFlow data\n- Security event data (MobieXpert, MobiWatch)\n- Service status data\n\n## 🚀 Quick Start\n\n### Basic Usage\n\n```python\nfrom MobiLLM import MobiLLM_Multiagent\n\n# Initialize the agent\nagent = MobiLLM_Multiagent()\n\n# Chat with the agent\nresponse = agent.chat(\"How many UEs are connected to the network?\")\nprint(response[\"output\"])\n\n# Security analysis\nresult = agent.security_analysis(\"Analyze event ID 123 for security threats\")\nprint(result[\"output\"])\n```\n\n### Security Analysis Example\n\n```python\n# Conduct security analysis\nresult = agent.invoke(\"\"\"[security analysis] \nEvent Details:\n- Source: MobieXpert\n- Name: RRC Null Cipher\n- Cell ID: 20000\n- UE ID: 54649\n- Severity: Critical\n- Description: UE uses null cipher mode in RRC session\n\"\"\")\n\nprint(\"Threat Summary:\", result[\"threat_summary\"])\nprint(\"MITRE Techniques:\", result[\"mitre_technique\"])\nprint(\"Countermeasures:\", result[\"countermeasures\"])\n```\n\n## 🧪 Testing\n\n### Run Test Suite\n\n```bash\n# Run all tests\npython -m MobiLLM.test.test_llm\n\n# Run baseline tests\npython -m MobiLLM.test.baseline\n```\n\n### Test Individual Components\n\n```bash\n# Test LLM functionality\npython -m MobiLLM.test_llm\n\n# Test specific agents\npython -c \"\nfrom MobiLLM import MobiLLM_Multiagent\nagent = MobiLLM_Multiagent()\nprint('Agent initialized successfully')\n\"\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F5GSEC%2FMobiLLM","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F5GSEC%2FMobiLLM","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F5GSEC%2FMobiLLM/lists"}