head to head · open source
pentest-ai-agents vs hol-guard
pentest-ai-agents has 2,248 GitHub stars, 429 forks, 1 open issues and last shipped 1 months ago. hol-guard has 630 stars, 76 forks, 94 open issues and last shipped today. pentest-ai-agents leads on adoption by 257% (2,248 vs 630 stars). pentest-ai-agents is written in Shell under MIT; hol-guard is written in Python under Apache-2.0. pentest-ai-agents has attracted 19% as many forks as stars, hol-guard 12%. hol-guard was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 3 topic tags (ai-agents, ai-security, claude-code), 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 20902 open source comparisons
Side by side
| pentest-ai-agents | hol-guard | |
|---|---|---|
| GitHub stars | ★ 2.2K | ★ 630 |
| License | MIT | Apache-2.0 |
| Written in | Shell | Python |
| Last push | 2026-08-16 | 2026-09-20 |
| Forks | ⑂ 429 | ⑂ 76 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick pentest-ai-agents if
- You weight community size — 2.2K stars and counting
- You want the MIT license terms
- Your stack matches Shell
- You value the larger contributor base for long-term maintenance
pick hol-guard if
- You want the hol-guard feature set and don't need the biggest community
- You prefer the Apache-2.0 license terms
- Your stack matches Python
- You evaluated both and hol-guard fits your workflow better
About pentest-ai-agents
pentest ai agents: 50 Claude Code subagents for authorized offensive security research. Lives in Claude Code ecosystem. Agents carry domain knowledge for recon, web, Active Directory, cloud, mobile, wireless, social engineering, payload crafting, reverse engineering, exploit chaining, detection engineering, forensics.
read the full pentest-ai-agents overview →
About hol-guard
HOL Guard is an open source, local first antivirus for AI agents that reviews shell commands, file access, package installs, and MCP tool calls before they run, built for developers and platform security teams running coding agents such as Claude Code, Codex, Cursor, and Gemini CLI.
read the full hol-guard overview →
More in AI & Machine Learning
Related comparisons
More AI Security & Privacy projects
Compare either of these against the rest of the AI Security & Privacy field.
Frequently asked questions
Is pentest-ai-agents or hol-guard more popular?
pentest-ai-agents has 2,248 GitHub stars and hol-guard has 630. pentest-ai-agents has the larger community by that measure.
Are pentest-ai-agents and hol-guard free?
Both are open source. pentest-ai-agents is licensed under MIT and hol-guard under Apache-2.0. Neither carries a licence fee.
What is the difference between pentest-ai-agents and hol-guard?
pentest-ai-agents is written in Shell and hol-guard 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, pentest-ai-agents or hol-guard?
Choose pentest-ai-agents if you want the larger community (2,248 stars) or its MIT licence terms. Choose hol-guard if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.