A cybersecurity incident response testing tool that uses LLMs and MITRE ATT&CK/ATLAS to generate tailored tabletop exercise scenarios from threat actor groups.
1.3K169PythonGPL-3.0Well maintainedUpdated 6 days ago
mrwadams/stride-gpt
AI-powered threat modeling tool that uses LLMs to generate STRIDE threat models, attack trees and mitigations for an application.
- Stars
- 1,152
- Forks
- 337
- Open issues
- 21
- Last commit
- 11 hours ago
What is it?
STRIDE GPT takes a description of an application, such as its type, authentication methods, and whether it is internet-facing or handles sensitive data, and uses a large language model to produce a threat model organized by the STRIDE categories. It can also generate attack trees, suggest mitigations, score threats with DREAD, and produce Gherkin test cases from the identified threats.
The project ships as a pip-installable command-line tool with an interactive REPL, a Streamlit web interface, and a Docker image. The CLI can analyze a codebase autonomously, using an agent that plans, reads files and synthesizes findings across subsystems. Outputs are available as Markdown, JSON, SARIF and a self-contained HTML report, with threats mapped to MITRE ATT&CK and ATLAS technique IDs.
Model access goes through LiteLLM, covering OpenAI, Anthropic, Google, Mistral, Groq, DeepSeek, OpenRouter and local LM Studio servers. The tool stores no application details between sessions.
Key features
- 01Generates STRIDE-based threat models, attack trees, mitigations and DREAD risk scores from an application description.
- 02Agentic CLI analysis of a codebase, with a planner, per-subsystem exploration and a synthesis pass.
- 03Data flow diagram generation and an embedded draw.io editor for architecture diagrams.
- 04Threat annotations for MITRE ATT&CK and ATLAS, plus OWASP LLM and agentic AI risk guidance.
- 05Output as Markdown, JSON, SARIF, or a shareable HTML report.
- 06Works with multiple LLM providers through LiteLLM, including local LM Studio servers.
Use cases
- Drafting a first-pass threat model for a new feature or service during design review.
- Running automated STRIDE analysis over a codebase and importing SARIF results into code scanning tools.
- Generating threat-based test cases to feed into QA or security testing.
- Threat modeling GenAI or agentic AI applications against OWASP LLM and ASI risk categories.
Quick start
- 1
Install the package with pip
pip install stride-gpt - 2
Check the installed version to confirm it works
stride-gpt --version
Things to know
- Needs access to an LLM provider, such as a paid API key or a locally hosted model server.
- Rapidly changing project with frequent large feature changes between versions.
In collections
Topics
#threat-modeling#security#stride#llm#ai-security#attack-trees#mitre-attack#sarif#application-security#cybersecurity
FAQ
- What is stride-gpt?
- AI-powered threat modeling tool that uses LLMs to generate STRIDE threat models, attack trees and mitigations for an application. STRIDE GPT takes a description of an application, such as its type, authentication methods, and whether it is internet-facing or handles sensitive data, and uses a large language model to produce a threat model organized by the STRIDE categories. It can also generate attack trees, suggest mitigations, score threats with DREAD, and produce Gherkin test cases from the identified threats.
- Is stride-gpt free to use? What license does it have?
- stride-gpt is open source under the MIT license. Check the license terms before using it in commercial products.
- Is stride-gpt still maintained?
- Actively maintained. The last commit to stride-gpt was on Nov 7, 2026.
- What can I use stride-gpt for?
- Drafting a first-pass threat model for a new feature or service during design review. Running automated STRIDE analysis over a codebase and importing SARIF results into code scanning tools. Generating threat-based test cases to feed into QA or security testing. Threat modeling GenAI or agentic AI applications against OWASP LLM and ASI risk categories.
- How do I install stride-gpt?
- Install the package with pip: pip install stride-gpt Check the installed version to confirm it works: stride-gpt --version
- Where can I get stride-gpt?
- The source code and installation instructions are on GitHub: https://github.com/mrwadams/stride-gpt
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Self-hostable open-source AI Security Operations Center that correlates alerts, runs LLM-agent triage with auditable logs, and proposes human-approved responses.
6.7K+1.1K this week718PythonMITUpdated 4 hours ago
A CLI and TypeScript SDK from OpenAI for scanning code for security vulnerabilities, validating findings, and generating fixes.
11.3K+56 this week911TypeScriptApache-2.0Updated 8 hours ago
Reference implementation of an autonomous vulnerability discovery and patching pipeline for Claude, with interactive security skills for threat modeling, scanning, triage, and patching.
7.7K+30 this week637PythonOtherUpdated 3 months ago
A collection of concise, topic-specific OWASP guides offering practical good security practices for developers building applications.
33.9K+115 this week4.7KJavaScriptCC-BY-SA-4.0Updated 2 days ago
Rust security scanner that audits MCP servers and AI agent skill files for prompt injection, tool poisoning, secret leakage and supply-chain risks.
99+1 this week20RustApache-2.0Well maintainedUpdated last month