# mrwadams/stride-gpt

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.

Repository: https://github.com/mrwadams/stride-gpt
Canonical: https://ross.abutalabs.com/products/stride-gpt
Homepage: https://stridegpt.streamlit.app
Language: Python
License: MIT
License Family: permissive
Topics: ai-security, application-security, attack-trees, cybersecurity, dread, generative-ai, llm, mcp, mitre-attack, security-tools, streamlit, stride, threat-modeling
Last push: 2026-09-02T10:43:17+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 61, longevity 88
- inputs: {"age_days": 1241, "days_push": 0, "days_rel": 45, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1112, forks 323 (observed 2026-09-03T02:15:15.314619+00:00)

## What it is
STRIDE GPT is an AI-powered threat modeling tool that uses LLMs to generate STRIDE-based threat models, attack trees, and MITRE ATT&CK/ATLAS mappings for applications. It offers a Streamlit web UI, a CLI with an interactive REPL, and agentic codebase analysis including GenAI and agentic AI system threat modeling.

## Use cases
- generate a STRIDE threat model for my application
- create attack trees from an app description
- threat model an LLM or agentic AI system
- map threats to MITRE ATT&CK techniques
- analyze a codebase for security threats automatically
- produce threat models in markdown, HTML, or SARIF

## When to choose
- you need fast, AI-assisted threat modeling during design or security review
- you want STRIDE/DREAD structure with MITRE ATT&CK and ATLAS mappings
- you are threat modeling GenAI or agentic AI applications
- you prefer a self-hosted tool with CLI, REPL, or web UI

## When to avoid
- you need guaranteed-complete or compliance-certified threat models without expert review
- you cannot send application details to external LLM APIs
- you need offline operation without any LLM access

## Facets
- artifact type: application
- maturity: active
- function: security, llm-inference, agent-framework, cli, developer-tools
- domain: security, developer-tools, artificial-intelligence, large-language-models
- platform: python, cli, cross-platform, self-hosted
- tags: threat-modeling, stride, dread, mitre-attack, attack-trees, appsec, owasp, streamlit, generative-ai, agentic-ai, web-server

## Member repositories
- mrwadams/stride-gpt (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:15.314619+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:44:02.759185+00:00, confidence not recorded.
  - readme: https://github.com/mrwadams/stride-gpt (fetched 2026-09-03T02:15:15.314619+00:00, sha f79557ec04f7)
  - registry_pypi: https://pypi.org/pypi/stride-gpt/json (fetched 2026-08-29T12:48:07.803579+00:00, sha 2e004512223a)
- Data as of 2026-08-30T08:39:29.467469+00:00.