The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
OpenDerisk
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent manager provides 7* 24-hour comprehensive and in-depth protection.
Install
git clone https://github.com/derisk-ai/OpenDeriskInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →OpenDeRisk
OpenDeRisk is an AI-Native Risk Intelligence System designed as your application system's intelligent manager, providing 7×24 hour comprehensive and in-depth protection.
English | 简体中文 | 日本語 | Video Tutorial
Features
- DeepResearch RCA: Quickly locate root causes through in-depth analysis of logs, traces, and code.
- Visualized Evidence Chain: Fully visualize diagnostic processes and evidence chains for clear, accurate judgment.
- Multi-Agent Collaboration: SRE-Agent, Code-Agent, ReportAgent, Vis-Agent, and Data-Agent working in coordination.
- Open-Source Architecture: Built with a completely open architecture, enabling framework and code reuse in open-source projects.
Architecture
Introduction
The system employs a multi-agent architecture. Currently, the code primarily implements the highlighted components. Alert awareness is based on Microsoft's open-source OpenRCA dataset. The decompressed dataset is approximately 26GB. On this dataset, we achieve root cause analysis through multi-agent collaboration, with Code-Agent dynamically writing code for final analysis.
Technical Implementation
Data Layer: Pull the large-scale OpenRCA dataset (20GB) from GitHub, decompress locally, and process for analysis.
Logic Layer: Multi-agent architecture with SRE-Agent, Code-Agent, ReportAgent, Vis-Agent, and Data-Agent collaborating for deep 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 multi-role collaboration and switching process.
Digital Employees (Agents) in OpenDeRisk
Install (recommended)
Install via curl
# Download and install latest version
curl -fsSL https://raw.githubusercontent.com/derisk-ai/OpenDerisk/main/install.sh | bash
Configuration File
After installation, the default configuration file is automatically initialized at:
~/.openderisk/configs/derisk-proxy-aliyun.toml
Edit this file and set your API keys:
vi ~/.openderisk/configs/derisk-proxy-aliyun.toml
Start
openderisk-server
From source(development)
Install uv (required)
macOS/Linux:
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows:
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
Clone and Install Dependencies
git clone https://github.com/derisk-ai/OpenDerisk.git
cd OpenDerisk
# Install Dependencies with uv
uv sync --all-packages --frozen \
--extra "base" \
--extra "proxy_openai" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "derisks" \
--extra "storage_oss2" \
--extra "client" \
--extra "ext_base" \
--extra "channel_dingtalk"
Note:
channel_dingtalkis optional. Skip it if you don't need DingTalk channel support.
Start Server
🚀 Quick Start (Zero Configuration, Recommended)
Start without any configuration file:
# Method 1: Use quickstart command
uv run derisk quickstart
# Method 2: Use startup script
./start.sh
# Method 3: Specify port
uv run derisk quickstart -p 8888
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io