OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Security & Safety

Stride Gpt

Stride Gpt is an LLM-powered application security tool that generates STRIDE threat models and attack trees from application details or codebase analysis. It provides a Streamlit web interface and a separate Python CLI.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Stride Gpt — OpenViST project profile in AI Security & Safety.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it during application design or security review when you can provide system context, or when a CLI-based analysis of a codebase would help organize threat discovery.

Who it is for

  • Security practitioners assessing application threats.
  • Developers and architecture teams preparing or reviewing application designs.
  • Teams that want CLI-based threat modeling or codebase analysis.

Documented uses

  • Generate a STRIDE threat model from application characteristics such as authentication, internet exposure and sensitive-data handling.
  • Explore possible attack paths with generated attack trees.
  • Analyze a codebase through the CLI and export findings in formats including JSON, SARIF and HTML.
Before you choose

Requirements & limits

The project is open source under the MIT license. The README documents a pip-installable CLI, a Streamlit interface available through source setup, and a Docker image for the web UI.

  • The web UI and CLI have distinct installation paths; pip installs the CLI only.
  • Codebase analysis makes many LLM calls, and token usage and cost scale with codebase size and model choice.
  • The README says application details are not stored.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the Python CLI

Set up the command-line interface for text-based threat modeling or codebase analysis.

Before you start

  • Python package installation with pip, or a local clone of the repository and uv for source setup.

Steps

  1. Install the CLI with the command below, or clone the repository and run the command below for the CLI and Streamlit web dependencies.

    Documented command
    pip install stride-gpt
    Documented command
    uv sync

  2. Configure provider API keys using environment variables, the interactive REPL /config command, or the Streamlit interface.

  3. Start the CLI with stride-gpt to open the interactive REPL.

Expected outcome

The CLI is installed and configured for interactive use; its quick mode accepts a text description, while `analyze` is documented for codebase analysis.

Guide limitations

  • The pip installation is CLI-only; the Streamlit web interface dependencies are included in the source setup.
  • Agentic analysis makes many LLM calls, with token use and cost varying by codebase size and model.
Documentation 1 ↗
Source-based practical guide

Run the Streamlit web interface in Docker

Start the documented web UI container image.

Before you start

  • Docker.

Steps

  1. Pull the image with the command below.

    Documented command
    docker pull mrwadams/stridegpt:latest

  2. Configure provider API keys using the Streamlit interface or environment variables.

Expected outcome

The web UI image is available to run in a Docker environment.

Guide limitations

  • The README provides the image-pull command but not a container run command in the cited installation section.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
mrwadams/stride-gpt · Official homepage title · retained in its source language
How we review sourcesSuggest a correction