head to head · open source

codex-security vs giskard-oss

codex-security has 11,287 GitHub stars, 903 forks, 220 open issues and last shipped yesterday. giskard-oss has 5,940 stars, 560 forks, 64 open issues and last shipped yesterday. codex-security leads on adoption by 90% (11,287 vs 5,940 stars). codex-security is written in TypeScript under Apache-2.0; giskard-oss is written in Python under Apache-2.0. codex-security has attracted 8% as many forks as stars, giskard-oss 9%. codex-security was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (ai-security), 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 giskard-oss ★ 5.9K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

codex-security giskard-oss
GitHub stars ★ 11K ★ 5.9K
License Apache-2.0 Apache-2.0
Written in TypeScript Python
Last push 2026-11-02 2026-11-02
Forks ⑂ 903 ⑂ 560
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 giskard-oss if

  • You want the giskard-oss 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 giskard-oss fits your workflow better

full giskard-oss 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 giskard-oss

Evals, Red Teaming and Test Generation for Agentic Systems Modular, Lightweight, Dynamic and Async first Docs • Website • Community [!IMPORTANT] Giskard v3 is a fresh rewrite designed for dynamic, multi turn testing of AI agents. This release drops heavy dependencies for better efficiency while introducing a more powerful AI vulnerability scanner and enhanced RAG evaluation — both now shipping natively in giskard scan , with no dependency on v2. Only the legacy scan for tabular/ML models remains v2 only. Giskard v2 remains available but is no longer actively maintained. Follow progress → Read the v3…

read the full giskard-oss 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 giskard-oss more popular?

codex-security has 11,287 GitHub stars and giskard-oss has 5,940. codex-security has the larger community by that measure.

Are codex-security and giskard-oss free?

Both are open source. codex-security is licensed under Apache-2.0 and giskard-oss under Apache-2.0. Neither carries a licence fee.

What is the difference between codex-security and giskard-oss?

codex-security is written in TypeScript and giskard-oss 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, codex-security or giskard-oss?

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