AgentDojo
5.4#24 in ai security testing toolsAPILinuxSelf-hosted
VisitAgentDojo vs Promptfoo
What both publish
| Fact | AgentDojo | Promptfoo |
|---|---|---|
| License | The project's GitHub page identifies its license as MIT. | The open-source project is distributed under the MIT license. |
| Model providers | Documented tool-calling LLM implementations support OpenAI, Anthropic, Google, and Cohere; the docs also describe using Llama 3 70B through TogetherAI’s API. | Provider documentation covers OpenAI, Anthropic, Google, Vertex, HTTP, JavaScript, Python, Ruby, shell, OpenAI Agents, and other services. |
AgentDojo plans
No prices published.
Promptfoo plans
- CommunityFree
- EnterprisePriced on request
- On-PremisePriced on request
Pick AgentDojo if…
It suits researchers building benchmarks and evaluating prompt-injection defenses in self-hosted LLM-agent pipelines.
Pick Promptfoo if…
Promptfoo suits developers and enterprise teams evaluating prompts, model outputs, and AI application risks. Its local and self-hosted options may appeal to teams that want to run the Community plan on their own infrastructure.