PentestGPT
Automated Penetration Testing Agentic Framework Powered by Large Language Models
GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
78views this month
Decision brief
PentestGPT is a Python-based automated penetration testing framework that uses large language models for security testing.
Good fit when
- When you need an automated penetration testing tool that leverages large language models for enhanced security analysis.
- For educational purposes or authorized security testing where Python-based solutions are preferred.
Avoid when
- If your project requires a tool that does not use large language models for penetration testing.
- When you need a tool that does not support Docker or does not offer persistent login sessions.
Observed Sep 18, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (65d since push)
- As of Sep 18, 2026
- Provenance
- Not a fork · Personal account
- As of Sep 18, 2026
- Security (OSV)
- No lockfile
- As of Sep 18, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install PentestGPTHow it fits your stack(7)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
A Python-based automated penetration testing framework that leverages large language models for security testing.
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Sep 18, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Sep 18, 2026
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Sep 18, 2026
- Languages
- python
Source: github.language+pyproject.toml · Sep 18, 2026
Categories
Tags
README
Installation Watch on YouTube Installation Run in Docker (install once, log in once) A self contained image bundles the tool + the Claude Code and Codex CLIs. You log in once and the sessions persist in named volumes — no re login on later runs. `` LICENSE.md` for more informatio...
For agents
This page has a .md twin and JSON over the API.