Modern software systems rarely live in a single repository. Architecture is spread across many services, libraries, and teams, and the connections between them are easy to lose track of — leaving the true shape of a system documented only in people's heads. Keeping an accurate, shared picture of how everything fits together is one of the hardest parts of working on large systems.

SysML Repo Modeler makes that picture explicit. Its AI analysis harness uses OpenCode to read one repository or many as a single system, then generates a formal SysML v2 architecture model from the source.

The result is an interactive graph you can explore: drill into architecture elements, trace repository-to-repository connectivity, and review how the pieces of a system actually relate. The application is self-hosted, so your source and the models generated from it stay within your own environment.

1. Sync the repositories. Add the GitHub repositories that make up the system. Public and private repositories can be analyzed together in one project workspace.
2. Read the system as a whole. OpenCode analyzes the repositories in two passes: first identifying structure and connections, then enriching the model with component purpose and detail.
3. Validate and repair. The harness checks whether the generated SysML v2 is renderable and covers the architecture found in the source. Targeted repair and coverage prompts improve the model without repeating discovery from scratch.
4. Explore the result. Review the generated model as SysML v2 code or as an interactive graph. Search parts and ports, filter connections, and drill into individual components.

These models were regenerated from pinned source commits and checked against the runtime and deployment code—not drawn by hand. Click any image to open the interactive model, inspect its connections, and drill into individual parts.

Explore SysML Repo Modeler on Belvedere Labs

The fastest way to run the complete local stack is Docker Compose. It builds and starts every service and serves the app at http://localhost:8080.

Prerequisites: Docker with Docker Compose, and an OpenAI API key for the OpenCode runtime.

1. Create your environment file from the template:

copy .env.example .env

2. Add your OpenAI API key to the new .env file:

OPENAI_API_KEY=sk-...

This is the only value you must set; every other variable has a working default for local use.

3. Build and start the stack:

docker compose up --build

4. Use the app. Open http://localhost:8080. The app has three views in the top navigation — Projects, Interconnections, and Code.

Start in the Projects view, where you manage projects and their repositories:

• Create a project. A project is the container for a set of related repositories that you want to model together — typically the repositories that make up one system. From the Projects view you can also rename, modify, or delete a project and the repositories it contains.

• Add repositories. Add the GitHub repositories that belong to the project by URL. For private repositories enter a GitHub token in the UI before importing. Tokens are used transiently and never stored. For a small public first run, try:

  https://github.com/pallets/click.git
  

• Sync Repos. Syncing clones any repositories that aren't present yet and pulls the latest changes for ones that are, bringing the project's local workspace up to date with the remotes. Run it after adding repositories, and again whenever you want to analyze newer code.

• Scan. A scan starts an analysis run over the synced workspace: OpenCode reads the source across all of the project's repositories and generates a SysML v2 architecture model. Each scan is saved as a versioned run you can revisit, compare, and inspect for diagnostics.

Once a scan completes, review the result in the other two views:

• Interconnections. Click the Interconnections button to explore the generated model as an interactive graph — drill into architecture elements and trace how repositories and components connect.
• Code. Click the Code button to view the current graph rendered as SysML v2 textual syntax.

Copy .env.example to .env. For local Docker Compose, the only variable you must set is OPENAI_API_KEY; the rest have working defaults.

GitHub credentials are supplied through the UI at import/sync time, not via environment variables. They are used transiently and not stored. For private repositories, use an HTTPS URL and enter a token in the UI before importing.

To run from source with Vite hot reload and a locally running backend, see DEVELOPMENT.md . Unlike the Docker Compose path, source development does not start Postgres or OpenCode for you — point the app at your own instances, or start just those two with docker-compose.dev.yml.

Contributions are welcome! See CONTRIBUTING.md for the development workflow, coding standards, and pull request process, and our Code of Conduct for community expectations.

SysML Repo Modeler is open-source software licensed under the MIT License.