head to head · open source
garak vs Adrian
garak has 9,850 GitHub stars, 1,439 forks, 429 open issues and last shipped 3 days ago. Adrian has 589 stars, 96 forks, 6 open issues and last shipped 15 days ago. garak leads on adoption by 1,572% (9,850 vs 589 stars). garak is written in Python under Apache-2.0; Adrian is written in Python under Apache-2.0. garak has attracted 15% as many forks as stars, Adrian 16%. garak was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai, llm-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.
← all 20902 open source comparisons
Side by side
| garak | Adrian | |
|---|---|---|
| GitHub stars | ★ 9.8K | ★ 589 |
| License | Apache-2.0 | Apache-2.0 |
| Written in | Python | Python |
| Last push | 2026-11-02 | 2026-10-21 |
| Forks | ⑂ 1.4K | ⑂ 96 |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick garak if
- You weight community size — 9.8K 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 Adrian if
- You want the Adrian 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 Adrian fits your workflow better
About garak
garak, LLM vulnerability scanner Generative AI Red teaming & Assessment Kit garak checks if an LLM can be made to fail in a way we don't want. garak probes for hallucination, data leakage, prompt injection, misinformation, toxicity generation, jailbreaks, and many other weaknesses. If you know nmap or msf / Metasploit Framework, garak does somewhat similar things to them, but for LLMs. garak focuses on ways of making an LLM or dialog system fail. It combines static, dynamic, and adaptive probes to explore this. garak 's a free tool. We love developing it and are always interested in adding functionality to…
read the full garak overview →
About Adrian
Agent attacks slip past static analysis and network monitoring. Adrian catches them at runtime, by watching what the agent actually does (its actions and its reasoning) and stepping in before it acts. Open source, free forever. +35% detection accuracy · 4x more nuanced attacks caught vs behaviour only monitoring ( OpenAI & DeepMind research ) ⭐ If you think agents need a runtime security layer, star the repo. It is how new people find Adrian, and how we know to keep building it in the open. Adrian is an open source, AARM aligned runtime security monitoring and control engine for AI agents. It analyses both agent…
read the full Adrian 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 garak or Adrian more popular?
garak has 9,850 GitHub stars and Adrian has 589. garak has the larger community by that measure.
Are garak and Adrian free?
Both are open source. garak is licensed under Apache-2.0 and Adrian under Apache-2.0. Neither carries a licence fee.
What is the difference between garak and Adrian?
garak is written in Python and Adrian 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, garak or Adrian?
Choose garak if you want the larger community (9,850 stars) or its Apache-2.0 licence terms. Choose Adrian if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.