AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
OpenDeRisk AI-Native Risk Intelligence Systems —— Your application system risk intelligent manager provides 7 * 24-hour comprehensive and in-depth protection.
The system adopts a multi-agent architecture. Currently, the code mainly implements the green-highlighted parts. Alert awareness is based on Microsoft's open-source OpenRCA dataset. The dataset size is approximately 26GB after decompression. On this dataset, we achieve root cause analysis and diagnosis through multi-agent collaboration, where the Code-Agent dynamically writes code for final analysis.
Data Layer: Pull the large-scale OpenRCA dataset (20GB) from GitHub, decompress it locally, and process it for analysis.
Logic Layer: Multi-agent architecture, with collaboration among SRE-Agent, Code-Agent, ReportAgent, Vis-Agent, and Data-Agent to perform in-depth DeepResearch RCA (Root Cause Analysis).
Visualization Layer: Use the Vis protocol to dynamically render the entire processing flow and evidence chain, as well as the process of multi-role collaboration and switching.
Digital Employees (Agents) in OpenDeRisk
Install uv
curl -LsSf https://astral.sh/uv/install.sh | sh
uv sync --all-packages --frozen \
--extra "base" \
--extra "proxy_openai" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "client"
Configure the API_KEY in the derisk-proxy-deepseek.toml file, then run the following command to start.
Note: By default, we use the Telecom dataset from the OpenRCA dataset. You can download it via the link or the following command:
gdown https://drive.google.com/uc?id=1cyOKpqyAP4fy-QiJ6a_cKuwR7D46zyVe
After downloading, modify the dataset path in the file basic_prompt_Telecom.py to the local absolute path.
Run the startup command:
uv run python packages/derisk-app/src/derisk_app/derisk_server.py --config configs/derisk-proxy-deepseek.toml
Open your browser and visit http://localhost:7777
As shown in the figure below, this demonstrates a scenario where multiple agents collaborate to handle a complex operational diagnostic task.
The OpenDeRisk-AI community is dedicated to building AI-native risk intelligence systems. 🛡️ We hope our community can provide you with better services, and we also hope that you can join us to create a better future together. 🤝
Join our networking group on Dingding and share your experience with other developers!
{ "mcpServers": { "openderisk": { "command": "uv", "args": [ "run", "python", "packages/derisk-app/src/derisk_app/derisk_server.py", "--config", "configs/derisk-proxy-deepseek.toml" ] } } }
Related projects feature coming soon
Will recommend related projects based on sub-categories