✨ A fully autonomous AI Agent capable of performing complex penetration testing tasks
100K+
⠀
Join the Community! Connect with security researchers, AI enthusiasts, and fellow ethical hackers. Get support, share insights, and stay updated with the latest PentAGI developments.
Penetration testing Artificial General Intelligence - A fully autonomous AI Agent capable of performing complex penetration testing tasks using terminal, browser, editor, and external search systems.
1. Create a working directory:
mkdir pentagi && cd pentagi
2. Download configuration files:
curl -O https://raw.githubusercontent.com/vxcontrol/pentagi/master/.env.example
curl -O https://raw.githubusercontent.com/vxcontrol/pentagi/master/docker-compose.yml
3. Configure environment:
cp .env.example .env
# Edit .env file with your API keys and settings
4. Run PentAGI:
docker compose up -d
5. Access the UI at https://localhost:8443 (default is [email protected] / admin)
OPEN_AI_KEY or ANTHROPIC_API_KEY: At least one LLM provider keyGOOGLE_API_KEY & GOOGLE_CX_KEY: For Google search integrationTAVILY_API_KEY: For Tavily search integrationTRAVERSAAL_API_KEY: For Traversaal search integrationPROXY_URL: Global proxy for external servicesPUBLIC_URL: Public URL of your serverPENTAGI_POSTGRES_USER & PENTAGI_POSTGRES_PASSWORD: PostgreSQL credentialsSERVER_SSL_CRT & SERVER_SSL_KEY: Custom SSL certificate pathsQuick setup:
# 1. Enable OpenTelemetry integration
echo "OTEL_HOST=otelcol:8148" >> .env
# 2. Download and start the monitoring stack
curl -O https://raw.githubusercontent.com/vxcontrol/pentagi/master/docker-compose-observability.yml
docker compose -f docker-compose.yml -f docker-compose-observability.yml up -d
Access Grafana at http://localhost:3000
Learn more about monitoring setup →
Quick setup:
# 1. Enable Langfuse integration
echo "LANGFUSE_BASE_URL=http://langfuse-web:3000" >> .env
# 2. Download and start the analytics stack
curl -O https://raw.githubusercontent.com/vxcontrol/pentagi/master/docker-compose-langfuse.yml
docker compose -f docker-compose.yml -f docker-compose-langfuse.yml up -d
Access Langfuse at http://localhost:4000
Learn more about analytics setup →
Note: For production use, you should properly configure security settings and credentials in the
.envfile. See the full documentation for details.
Tip: To run both monitoring and analytics stacks together:
docker compose -f docker-compose.yml -f docker-compose-langfuse.yml -f docker-compose-observability.yml up -d
Full documentation available at:
Copyright (c) PentAGI Development Team. MIT License
Content type
Image
Digest
sha256:2c22b0169…
Size
273.4 MB
Last updated
about 2 months ago
docker pull vxcontrol/pentagi