head to head · open source
Anthropic-Cybersecurity-Skills vs PentestGPT
Anthropic-Cybersecurity-Skills has 32,970 GitHub stars, 3,985 forks, 48 open issues and last shipped 19 days ago. PentestGPT has 15,521 stars, 2,700 forks, 81 open issues and last shipped 2 months ago. Anthropic-Cybersecurity-Skills leads on adoption by 112% (32,970 vs 15,521 stars). Anthropic-Cybersecurity-Skills is written in Python under Apache-2.0; PentestGPT is written in Python under MIT. Anthropic-Cybersecurity-Skills has attracted 12% as many forks as stars, PentestGPT 17%. Anthropic-Cybersecurity-Skills was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (llm), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 15422 open source comparisons
Side by side
| Anthropic-Cybersecurity-Skills | PentestGPT | |
|---|---|---|
| GitHub stars | ★ 33K | ★ 16K |
| License | Apache-2.0 | MIT |
| Written in | Python | Python |
| Last push | 2026-08-31 | 2026-07-14 |
| Forks | ⑂ 4.0K | ⑂ 2.7K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick Anthropic-Cybersecurity-Skills if
- You weight community size — 33K stars and counting
- You want the Apache-2.0 license terms
- Your stack matches Python
- You value the larger contributor base for long-term maintenance
pick PentestGPT if
- You want the PentestGPT feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and PentestGPT fits your workflow better
About Anthropic-Cybersecurity-Skills
Anthropic Cybersecurity Skills is an Apache 2.0 Python library of 817 structured cybersecurity skills that gives AI agents the working knowledge of a senior security analyst, aimed at security teams, DevSecOps engineers, and red or blue teams that already run agents such as Claude Code, GitHub Copilot, Codex CLI, Cursor, or Gemini CLI.
read the full Anthropic-Cybersecurity-Skills overview →
About PentestGPT
PentestGPT is an MIT licensed Python framework that uses large language models to run automated penetration tests and CTF challenges, aimed at penetration testers, security engineers and CTF players who want an agent to drive the tooling rather than working through it by hand.
read the full PentestGPT overview →
More in Security & Privacy
Related comparisons
More Threat Detection & Response projects
Compare either of these against the rest of the Threat Detection & Response field.
Frequently asked questions
Is Anthropic-Cybersecurity-Skills or PentestGPT more popular?
Anthropic-Cybersecurity-Skills has 32,970 GitHub stars and PentestGPT has 15,521. Anthropic-Cybersecurity-Skills has the larger community by that measure.
Are Anthropic-Cybersecurity-Skills and PentestGPT free?
Both are open source. Anthropic-Cybersecurity-Skills is licensed under Apache-2.0 and PentestGPT under MIT. Neither carries a licence fee.
What is the difference between Anthropic-Cybersecurity-Skills and PentestGPT?
Anthropic-Cybersecurity-Skills is written in Python and PentestGPT in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, Anthropic-Cybersecurity-Skills or PentestGPT?
Choose Anthropic-Cybersecurity-Skills if you want the larger community (32,970 stars) or its Apache-2.0 licence terms. Choose PentestGPT if its feature set, stack or MIT licence fits better. Both are self-hostable.