agentdojo
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Test and evaluate different attacks and defenses for AI language models.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeA Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
agentdojo has 780 stars on GitHub. It has been forked 200 times. agentdojo is written mainly in Python. It has been in active development since 2024. agentdojo is available under the MIT license. Its main topics are benchmark, large-language-models, prompt-injection, security.
What is agentdojo?
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
Is agentdojo open source?
agentdojo is an open-source project. It is released under the MIT license.
Is agentdojo free?
Yes. agentdojo is free and open source — you can use, modify and self-host it.
What license does agentdojo use?
agentdojo is available under the MIT license.
What language is agentdojo written in?
agentdojo is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/ethz-spylab-agentdojo.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.