pentestcode

Terminal pentesting agent that runs specialist subagents over a shared engagement state and supports 20+ LLM providers

Agent by s0ld13rr

IndexedMIT★ 883

Write a review

Get started

Setup steps are in the repository. Repository

About

PentestCode is a beta AI penetration testing agent for the terminal, forked from OpenCode and rebuilt for offensive security. A lead agent dispatches 13 specialist subagents, such as recon, scanner and exploiter, and records findings with their evidence in a shared engagement state. It works with more than 20 model providers through the ai-sdk, including Anthropic, OpenAI, Google, Azure, AWS Bedrock and Ollama.

Use cases: security, security-scanning, agent-orchestration

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: securityREADME
Autonomy: Autonomous: runs tasks end to end and reports backREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: anthropic, openai, google, azure-openai, aws-bedrock, ollamaREADME
Open source: YesREADME

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Signals

Stars: 883
Forks: 139
Open issues: 3
Last commit: Oct 23, 2026 (5 days ago)
Last release: Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/s0ld13rr/pentestcode
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

More from s0ld13rr

Cite this page

pentestcode. Agent Mart. https://agentmart.dev/agents/pentestcode (last updated 2026-10-24)