repello-agent-wiz 0.1.0

Generate agentic workflows visualizations & threat modelling reports for your agentic projects.

Agent Wiz

Python CLI for extracting agentic workflows from popular AI frameworks and performing automated security analysis using threat modeling methodologies.

Designed for developers, researchers, and security teams, Agent Wiz enables the introspection of LLM-based orchestration logic to visualize flows, map tool/agent interactions, and generate security reports via structured threat modeling frameworks.

❓ Why Should You Use It?

In modern LLM-powered systems, agentic workflows are becoming increasingly complex — with dozens of autonomous agents, tools, and inter-agent communication chains. Agent Wiz helps you bring visibility, structure, and security to these otherwise opaque systems.

Key Benefits

• Understand Complex Agent Graphs
  Instantly get clear visibility of agentic workflows in your code, no manual tracing needed! The visualsation clearly specifies various types of connections that can exist in a agentic workflow like Agent-Agent edges, Agent-Tool edges, Tool-Tool chained edges, or even something like Agent Agent edgdes through an intermediate tool.

• Integrated Security Analysis
  Get instant threat modeling reports tailored to your actual orchestration logic. Perfect for audits, red-teaming, or compliance reviews.

• Developer & Researcher Friendly
  Simple CLI, extensible SDK, and clean JSON export — ideal for visualization, automation, or integrating with CI/CD pipelines.

• Framework Agnostic
  Works with all major LLM orchestration stacks like Autogen, LangGraph, CrewAI, LlamaIndex, Swarm, and more.

• Built for Scale & Insight
  Agent Wiz grows with your AI system. Whether you're prototyping or in production — it gives you introspection, fast.

Supported Frameworks

The following orchestration frameworks are currently supported:

Framework	Status
Autogen (core)	✅
AgentChat	✅
CrewAI	✅
LangGraph	✅
LlamaIndex	✅
n8n	✅
OpenAI Agents	✅
Pydantic-AI	✅
Swarm	✅

Each framework has its own AST-based static parser to extract:

• Agents (class/function-based)
• Tool functions
• Agent-to-agent transitions
• Tool call chains
• Group agents (e.g., selector, round-robin)

Security Analysis

Agent Wiz currently supports MAESTRO as its primary threat modeling framework. It evaluates agent workflows against the following structure:

• Mission
• Assets
• Entrypoints
• Security Controls
• Threats
• Risks
• Operations

Using LLM-backed analysis (GPT-4), a full security report is generated based on your workflow JSON. For example:

Before running any analysis commands, you must set your OpenAI API key as an environment variable:

export OPENAI_API_KEY=sk-...

You can also add this line to your .bashrc, .zshrc, or environment setup script for persistent use.

🧪 More threat models analysis (STRIDE, PASTA, LINDDUN, etc.) are under development.

Installation

pip install repello-agent-wiz

🚀 CLI Usage

1. Extract Agentic Workflow

agent-wiz --framework agent_chat --directory ./examples/code/agent_chat --output agentchat_graph.json

This will generate a graph JSON with the following structure:

{
  "nodes": [...],
  "edges": [...],
  "metadata": {
    "framework": "autogen"
  }
}

2. Visualize the Agentic workflow

agent-wiz --visualize --input agentchat_graph.json --open

This will generate an html d3 based visualisation of the agentic workflow. The open flag (optional) and automatically opens the visualization in your default browser.

3. Analyze against Threat Modeling

agent-wiz --analyze --input agentchat_graph.json

This will generate a report like: autogen_report.md based on the provided graph and threat modeling frameworks.

Run agent-wiz --help for more info:

usage: agent-wiz [-h] {extract,analyze,visualize} ...

Agent Wiz CLI: Extract, Analyze, Visualize agentic workflows.

positional arguments:
  {extract,analyze,visualize}
    extract             Extract graph from source code
    analyze             Run threat modeling analysis on extracted graph
    visualize           Generate HTML visualization from graph JSON

options:
  -h, --help            show this help message and exit

📈 Roadmap

Planned features (Not in any paricular order)

• Build parsers for major agentic frameworks (Autogen, LangGraph, CrewAI, etc.)
• Generate standardized JSON graph representations of agent flows
• CLI interfaces
• Security report generation
• Extend to STRIDE, PASTA, LINDDUN, etc.
• Agent simulation-based threat exploration

🤝 Contributing

We welcome contributions of all kinds!

⚠️ Please read CONTRIBUTING.md before submitting issues or PRs.

📜 Changelog

For recent changes and version history, see CHANGELOG.md.

📄 License

Licensed under the Apache 2.0 License. See LICENSE for full details.

Links

• Agent Wiz GitHub
• Issue Tracker
• PyPI Package