{"data":{"slug":"vxcontrol-pentagi","name":"pentagi","tagline":"Fully autonomous AI Agents system for complex penetration testing tasks","github_url":"https://github.com/vxcontrol/pentagi","owner":"vxcontrol","repo":"pentagi","owner_avatar_url":"https://avatars.githubusercontent.com/u/39194251?v=4","primary_language":"Go","stars":21902,"forks":2904,"topics":["ai-agents","ai-security-tool","anthropic","autonomous-agents","golang","gpt","graphql","multi-agent-system","offensive-security","open-source","openai","penetration-testing","penetration-testing-tools","react","security-automation","security-testing","security-tools","self-hosted"],"archived":false,"github_pushed_at":"2026-08-06T11:10:55+00:00","maintenance_label":"Active","stars_delta_30d":910,"url":"https://www.graphcanon.com/tools/vxcontrol-pentagi","markdown_url":"https://www.graphcanon.com/tools/vxcontrol-pentagi.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vxcontrol-pentagi","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vxcontrol-pentagi","description":"Fully autonomous AI Agents system capable of performing complex penetration testing tasks","homepage_url":"https://pentagi.com","license":"MIT","open_issues":46,"watchers":128,"ai_summary":"Provides an autonomous AI agents framework for performing complex security-related penetration testing tasks in a fully automated manner.","readme_excerpt":"## Quick Start\n\nFor a step-by-step walkthrough that connects installation, configuration, LLM and embedding provider testing, and your first login, see the [Installing and Configuring PentAGI](examples/guides/installation_configuration.md) guide. The sections below remain the detailed reference for each step.\n\n---\n\n### System Requirements\n\n- Docker and Docker Compose (or Podman - see [Podman configuration](#running-pentagi-with-podman))\n- Minimum 2 vCPU\n- Minimum 4GB RAM\n- 20GB free disk space\n- Internet access for downloading images and updates\n\n---\n\n# Create installation directory\nmkdir -p pentagi && cd pentagi\n\n---\n\n### Manual Installation\n\n1. Create a working directory or clone the repository:\n\n```bash\nmkdir pentagi && cd pentagi\n```\n\n2. Copy `.env.example` to `.env` or download it:\n\n```bash\ncurl -o .env https://raw.githubusercontent.com/vxcontrol/pentagi/master/.env.example\n```\n\n3. Touch examples files (`example.custom.provider.yml`, `example.ollama.provider.yml`) or download it:\n\n```bash\ncurl -o example.custom.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/custom-openai.provider.yml\ncurl -o example.ollama.provider.yml https://raw.githubusercontent.com/vxcontrol/pentagi/master/examples/configs/ollama-llama318b.provider.yml\n```\n\n4. Fill in the required API keys in `.env` file.\n\n```bash\n\n---\n\n# Optional: Local LLM provider (zero-cost inference)\nOLLAMA_SERVER_URL=http://localhost:11434\nOLLAMA_SERVER_MODEL=your_model_name\n\n---\n\n# Using pre-built Ollama Cloud configuration (included in Docker image)\nOLLAMA_SERVER_URL=https://ollama.com\nOLLAMA_SERVER_API_KEY=your_ollama_cloud_api_key\nOLLAMA_SERVER_CONFIG_PATH=/opt/pentagi/conf/ollama-cloud.provider.yml\n```\n\nThe pre-built `ollama-cloud.provider.yml` configuration includes optimized model assignments for all agent types:\n- **Simple/Assistant**: `nemotron-3-super:cloud` - Fast general-purpose model\n- **Primary Agent**: `qwen3-coder-next:cloud` - Advanced reasoning with high effort mode\n- **Coder/Pentester**: `qwen3-coder-next:cloud` - Specialized coding models\n- **Searcher**: `qwen3.5:397b-cloud` - Large context for information gathering\n- **Refiner/Refactor**: `glm-5:cloud` - High-quality text refinement\n- **Adviser/Enricher**: `minimax-m2.7:cloud` - Efficient advisory tasks\n- **Installer**: `devstral-2:123b-cloud` - Installation and setup tasks\n\n**Custom Configuration (Advanced)**\n\nTo create your own agent configuration, mount a custom file from your host filesystem:\n\n```bash\n\n---\n\n# Mount custom configuration from host filesystem (in .env or docker-compose override)\nPENTAGI_OLLAMA_SERVER_CONFIG_PATH=/path/on/host/my-ollama-config.yml\n```\n\nThe `PENTAGI_OLLAMA_SERVER_CONFIG_PATH` environment variable maps your host configuration file to `/opt/pentagi/conf/ollama.provider.yml` inside the container.\n\n**Example custom configuration** (`my-ollama-config.yml`):\n\n```yaml\nprimary_agent:\n  model: \"qwen3-coder-next:cloud\"\n  temperature: 1.0\n  top_p: 0.9\n  max_tokens: 32768\n  reasoning:\n    effort: high\n\ncoder:\n  model: \"qwen3-coder:32b\"\n  temperature: 1.0\n  max_tokens: 20480\n```\n\n#### Local Ollama Configuration\n\nFor self-hosted Ollama instances:\n\n```bash\n\n---\n\n# Using pre-built configurations from Docker image\nOLLAMA_SERVER_CONFIG_PATH=/opt/pentagi/conf/ollama-llama318b.provider.yml\n\n---\n\n### Docker Image Configuration\n\nPentAGI allows you to configure Docker image selection for executing various tasks. The system automatically chooses the most appropriate image based on the task type, but you can constrain this selection by specifying your preferred images:\n\n| Variable                           | Default                | Description                                                 |\n| ---------------------------------- | ---------------------- | ----------------------------------------------------------- |\n| `PENTAGI_IMAGE`                    | `vxcontrol/pentagi:latest` | Docker image used for the main PentAGI application service |\n| `DOCKER_DEFAU","github_created_at":"2025-01-06T22:22:48+00:00","created_at":"2026-07-07T17:40:44.804685+00:00","updated_at":"2026-08-20T00:01:08.381174+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai-agents","name":"ai-agents"},{"slug":"golang","name":"golang"},{"slug":"open-source","name":"open-source"},{"slug":"penetration-testing-tools","name":"penetration-testing-tools"},{"slug":"security-testing","name":"security-testing"}],"trust":{"provenance":{"is_fork":false,"github_id":913030762,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-20T00:01:07.629Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":1,"days_since_push":13,"last_release_at":"2026-05-29T18:25:21Z","stars_delta_30d":910,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:17:30.179Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-20T00:01:08.064Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-20T00:01:08.064Z","managed_saas":false},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-08-20T00:01:08.064Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-20T00:01:08.064Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-20T00:01:08.064Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Docker and Docker Compose (or Podman) is required","System must have a minimum of 2 vCPUs.","At least 20GB free disk space needed."],"min_ram_gb":4,"requires_docker":true},"constraints":{"min_ram_gb":4,"requires_docker":true},"when_to_use":["Use PentAGI when you need a fully autonomous solution for handling intricate penetration tests with minimal human intervention.","Choose PentAGI if your environment requires significant scalability and flexibility through the use of AI-driven agents, especially those capable of adapting strategies based on real-time data and API"],"when_not_to_use":["Avoid using PentAGI in scenarios where legacy systems cannot support Docker or require manual oversight for each penetration test step.","Do not utilize PentAGI if you prefer a proprietary model over open-source solutions, as it operates under the MIT license."],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:18:32.009Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM; Requires Docker; Docker and Docker Compose (or Podman) is required; System must have a minimum of 2 vCPUs.; At least 20GB free disk space needed."},{"label":"Adopt for","value":"PentAGI is a fully autonomous AI agent system specifically designed for complex penetration testing tasks, offering a comprehensive framework that operates in an automated fashion to enhance security evaluations."}]}}