Dev Tools
Continue
Open-source coding agent
★ 36.1k starsApache-2.0
View guide →// devtools · 0xSteph/pentest-ai-agents
pentest-ai-agents
pentest-ai-agents is an open-source dev tools project by 0xSteph (0xSteph/pentest-ai-agents on GitHub). It has 2,307 GitHub stars and 435 forks, is released under the MIT license, and was last updated on GitHub on 16 August 2026.
AI subagents that turn Claude Code into an authorized penetration-testing assistant.
💎 Hidden gem★ 2.3k stars⑂ 435 forksMITupdated 2026-08
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- 0xSteph/pentest-ai-agents
- GitHub stars
- 2,307
- Forks
- 435
- License
- MIT
- Last updated on GitHub
- 16 August 2026
- Category
- Dev Tools
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Pick an engagement phase
Choose the subagent that matches your task: planning, recon analysis, exploit research, or reporting.
- Run it inside Claude Code
The subagents plug into Claude Code, so your existing session and context stay intact.
- Work through the workflow
Recon findings feed exploit research, which feeds detection-building and report drafting.
- Review and authorize
Every step is human-in-the-loop — you approve actions before anything touches a target.
// features
Why people love it
Engagement planning
Structured subagents that plan authorized tests before any commands run.
Recon analysis
Sifts reconnaissance output into findings worth chasing.
Exploit research
Helps research known exploits against discovered services.
Detection building
Turns findings into detection rules for defenders.
STIG auditing
Checks systems against STIG hardening benchmarks.
Report writing
Drafts penetration-test reports from session notes.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/0xSteph/pentest-ai-agents.git cd pentest-ai-agents - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// use cases
What you can build
- Plan the phases of an authorized penetration test.
- Analyze recon data to prioritize targets worth testing.
- Research exploits and build matching detections.
- Audit configurations against STIG baselines.
Advertisement
// faq
Questions, answered
Is pentest-ai-agents free for commercial use?
MIT licensed — commercial use allowed with attribution.
Is this legal to use?
It is built for authorized testing only — you must have written permission for every target you touch.
Do I need Claude Code installed?
Yes — the subagents are designed to run inside Claude Code sessions.
Can it replace a human pentester?
No — it assists and accelerates, but judgment, scoping, and reporting stay human work.
How active is the project?
With 2307 stars and 435 forks it has a solid community; check recent commits to gauge current maintenance.
// keep exploring
Similar tools
Dev Tools
Aider
Aider is AI pair programming in your terminal
★ 49.4k starsApache-2.0
View guide →Dev Tools
OpenCode
The open source coding agent
★ 211.6k starsMIT
View guide →Dev Tools
agents-cli
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
★ 6.0k starsApache-2.0
View guide →Dev Tools
econ-writing-skill
Turn your AI assistant into an expert economics-paper writer.
★ 638 starsMIT
View guide →Dev Tools
oh-my-claudecode
Teams-first multi-agent orchestration for Claude Code — parallel agents, team mode and tmux workers
★ 39.7k starsMIT
View guide →// alternatives
Alternatives in Dev Tools
The most-starred other Dev Tools projects in the LibreAI catalogue — the realistic shortlist if pentest-ai-agents is not the right fit.
- OpenCode★ 211.6k
The open source coding agent
- Transformers★ 166.9k
The model-definition framework behind modern AI — thousands of pretrained transformers for text, vision, and audio.
- claude-code★ 149.7k
Anthropic's agentic coding tool that lives in your terminal and works across your whole codebase
- cc-switch★ 141.3k
Cross-platform desktop all-in-one manager for Claude Code, Codex, OpenCode and other coding agents
- codex★ 128.2k
OpenAI's lightweight coding agent that runs locally in your terminal
// more in devtools
More in Dev Tools
Nearby Dev Tools projects in the catalogue, closest in stars to pentest-ai-agents — keep exploring the shelf either side of it.
- DataDesigner★ 2.3k
NVIDIA NeMo Data Designer: build validated, multimodal synthetic datasets from scratch or from seed data.
- arc-kit★ 2.3k
AI-driven enterprise architecture governance — strategy, delivery and assurance harness.
- claude-skills-llm-council★ 2.3k
LLM Council — a Claude Code skill that runs your decisions through 5 AI advisors with peer review
- inspector★ 2.2k
MCPJam Inspector: chat with, inspect, debug, and evaluate MCP servers across clients and models.
- mcp2cli★ 2.4k
Turn any MCP server, OpenAPI spec or GraphQL endpoint into a CLI — at runtime, with zero codegen
- APIAuto★ 2.2k
Advanced HTTP API toolkit — no-code ML testing, AI docs and code generation.
Get pentest-ai-agents
Free and open — grab the source, star the repo, and start creating.