General agentSecurity and privacy
pentagi
Plan and run authorized penetration tests with autonomous agents in an isolated environment.
- Stars
- 20,544
- Forks
- 2,718
- Updated
- Updated Jul 14, 2026
MIT
Plan and run authorized penetration tests with autonomous agents in an isolated environment.
PentAGI lets autonomous agents plan and execute authorized penetration-testing work inside an isolated Docker environment. It includes more than twenty security tools such as nmap, Metasploit, and sqlmap, and can retain useful findings for later tasks. Cloud and local models are supported; smaller open models benefit from execution monitoring and task planning at the cost of higher token usage.
Resource types
Use cases
Runtime
Run supported always-on AI agents inside managed NVIDIA OpenShell sandboxes.
Scan agent skills for malicious instructions, unsafe code, and supply-chain risks
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Run a security-focused personal AI assistant on your own machine or server.
Install security auditing, vulnerability research, and development skills for Claude Code or Codex.