Community

Join the DTap community, and see how teams are measuring their own agents on the platform.

Join the Community

Join our Discord

Chat with a community of red-teaming experts to build secure agents with the DecodingTrust-Agent platform, get support and troubleshooting for the dataset and evaluating your agent, and more.

Accept Invite

Resources

Source Code

Explore and contribute to the DTap codebase.

github.com/decodingtrust-agent

Dataset

Access our evaluation datasets on HuggingFace.

huggingface.co/decodingtrust-agent

SDK / PyPI

Install the Python SDK for easy integration.

pypi.org/project/decodingtrust-agent

Research Paper

Read our technical paper on arXiv.

arxiv.org/abs/2605.04808

Citation

If you use DecodingTrust-Agent in your research, please cite our paper.

@article{chen2026decodingtrust,
  title={DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents},
  author={Chen, Zhaorun and Liu, Xun and Tong, Haibo and Guo, Chengquan and Nie, Yuzhou and Zhang, Jiawei and Kang, Mintong and Xu, Chejian and Liu, Qichang and Liu, Xiaogeng and others},
  journal={arXiv preprint arXiv:2605.04808},
  year={2026}
}

Contributing

We welcome contributions from the community! Here are some ways you can help:

→Submit bug reports and feature requests on GitHub
→Contribute new sandbox environments or attack vectors
→Improve documentation and tutorials
→Share your evaluation results on the leaderboard