PentAGI – Automated AI-Powered Penetration Testing Tool that Integrates 20+ Security Tools

PentAGI: AI-Driven Penetration Testing Tool

PentAGI introduces an AI-driven approach to penetration testing, automating complex workflows with tools such as Nmap and Metasploit while generating detailed reports.

Developed by VXControl and released on GitHub in early 2025 , this open-source platform enables security professionals to conduct autonomous assessments within isolated Docker environments.

The tool features fully autonomous AI agents that dynamically plan and execute penetration tests, integrating over 20 professional security tools, including Nmap for network discovery, Metasploit for exploitation, and sqlmap for database attacks.

Users specify a target, and PentAGI's multi-agent system, consisting of researcher, developer, and executor roles, orchestrates the process, utilizing long-term memory to recall past successes and adapt strategies.

This eliminates the need for manual scripting, allowing for rapid vulnerability identification and proof-of-concept exploits without compromising host systems, as all operations are conducted in a sandbox environment.

PentAGI's intelligence is enhanced through integrations with leading LLMs such as OpenAI, Anthropic Claude, Google Gemini , and local Ollama models, supporting flexible deployment from cloud APIs to on-premises inference.

External search APIs, including Tavily, Perplexity, and DuckDuckGo, provide real-time web intelligence, while a built-in scraper securely gathers target-specific data.

The system generates comprehensive reports with exploitation guides, stored persistently in PostgreSQL with pgvector for semantic querying, and visualized using Grafana dashboards for monitoring agent performance.

A sophisticated chain summarization mechanism prevents LLM context overflow, preserving critical conversation history through configurable QA pairs and byte-limited sections, ensuring coherent multi-turn reasoning even in extended penetration tests.

Parameter Environment Variable Default Description

Preserve Last SUMMARIZER_PRESERVE_LAST true Keep last section messages intact

Last Section Size SUMMARIZER_LAST_SEC_BYTES 51200 Max bytes for last section (50KB)

Max QA Size SUMMARIZER_MAX_QA_BYTES 65536 Max bytes for QA sections (64KB)

Assistant-specific settings allocate more context, up to 75KB, optimizing for complex exploit chains.

PentAGI employs a microservices architecture with a React/TypeScript frontend, Go-based REST/GraphQL backend, and asynchronous task queues for scalability.

Knowledge graphs via Neo4j and Graphiti track entity relationships, enhancing contextual understanding of vulnerabilities. Monitoring stacks such as OpenTelemetry, Jaeger, Loki, and VictoriaMetrics provide end-to-end observability, while Langfuse analyzes LLM traces.

Deployment is streamlined via Docker Compose: clone the repository, configure the .env file with API keys, and launch with a single command, accessible at localhost:8443.

Production setups support horizontal scaling, OAuth (GitHub/Google), and worker nodes for air-gapped execution. Security features include network isolation, TLS, and proxy support for LLM/search traffic.

PentAGI addresses key challenges such as tool chaining and report automation, positioning it among the leading open-source tools for 2026. Security teams can self-host for data control, though users must manage LLM costs and rate limits, particularly on AWS Bedrock.

Based on reporting by Cyber Security News.