head to head · open source

codex-security vs pentest-ai-agents

codex-security has 11,287 GitHub stars, 903 forks, 220 open issues and last shipped yesterday. pentest-ai-agents has 2,400 stars, 452 forks, 1 open issues and last shipped 28 days ago. codex-security leads on adoption by 370% (11,287 vs 2,400 stars). codex-security is written in TypeScript under Apache-2.0; pentest-ai-agents is written in Shell under MIT. codex-security has attracted 8% as many forks as stars, pentest-ai-agents 19%. codex-security was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai-security, cybersecurity), 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.

codex-security ★ 11K pentest-ai-agents ★ 2.4K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

codex-security pentest-ai-agents
GitHub stars ★ 11K ★ 2.4K
License Apache-2.0 MIT
Written in TypeScript Shell
Last push 2026-11-02 2026-10-06
Forks ⑂ 903 ⑂ 452
Self-hosting Yes Yes
Data ownership Your server Your server

pick codex-security if

  • You weight community size — 11K stars and counting
  • You want the Apache-2.0 license terms
  • Your stack matches TypeScript
  • You value the larger contributor base for long-term maintenance

full codex-security profile →

pick pentest-ai-agents if

  • You want the pentest-ai-agents feature set and don't need the biggest community
  • You prefer the MIT license terms
  • Your stack matches Shell
  • You evaluated both and pentest-ai-agents fits your workflow better

full pentest-ai-agents profile →

About codex-security

Codex Security @openai/codex security is a CLI and TypeScript SDK for defining security policy and finding, validating, and fixing security vulnerabilities in your code. 👉👉 See the Codex Security documentation for full documentation. Some cybersecurity requests and protected findings require approval through Trusted Access for Cyber. To join the program, visit chatgpt.com/cyber. Quick start Requires Node.js 22.13.0 or later and Python 3.10 or later. For CI, set OPENAI API KEY instead of signing in. Generate SECURITY.md Draft repository wide or component scoped SECURITY.md guidance for future scans: The command…

read the full codex-security overview →

About pentest-ai-agents

pentest ai agents 50 Claude Code subagents for penetration testing. Quick Start Cheatsheet Coverage Agents Examples Table of Contents What's New in v3.3 What's New in v3.2 Agent Map What's New in v3.1 Quick Start Cheatsheet Coverage Agents Tier 1 vs Tier 2 Examples Running Tools in a Container Findings Database Token Optimization Local Models Documentation MCP Server Prerequisites Legal License pentest ai agents is a collection of 50 Claude Code subagents that turn Claude into an offensive security research assistant. Each agent carries deep domain knowledge in a specific area: recon, web, Active Directory…

read the full pentest-ai-agents 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 codex-security or pentest-ai-agents more popular?

codex-security has 11,287 GitHub stars and pentest-ai-agents has 2,400. codex-security has the larger community by that measure.

Are codex-security and pentest-ai-agents free?

Both are open source. codex-security is licensed under Apache-2.0 and pentest-ai-agents under MIT. Neither carries a licence fee.

What is the difference between codex-security and pentest-ai-agents?

codex-security is written in TypeScript and pentest-ai-agents in Shell. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, codex-security or pentest-ai-agents?

Choose codex-security if you want the larger community (11,287 stars) or its Apache-2.0 licence terms. Choose pentest-ai-agents if its feature set, stack or MIT licence fits better. Both are self-hostable.