Architecture diagrams that actually run - turn static system maps into live control panels.
8.1K
Architecture diagrams that actually run, generated by AI agents.
Turn your static system architecture into a live control panel wired directly to your running application. Click a node, fire a real request, watch downstream services light up as your app emits events back.
docker run --rm -it -p 4321:4321 -v $(pwd):/workspace tuongaz/seeflow
Then open http://localhost:4321.
The studio scans /workspace/.seeflow/seeflow.json on start and auto-registers that flow if present.
Runtime environment variables:
| Variable | Default | Description |
|---|---|---|
SEEFLOW_PORT | 4321 | Port the studio listens on |
SEEFLOW_FLOW | .seeflow/seeflow.json | Flow file path relative to the workspace |
SEEFLOW_WORKSPACE | /workspace | Workspace mount point inside the container |
Ship a container that already contains your flow:
FROM tuongaz/seeflow
COPY ./my-demos /workspace
docker build -t my-flow .
docker run --rm -it -p 4321:4321 my-flow
:latest — newest stable release:<version> — pinned release (e.g. :0.1.18):<major>.<minor> — latest patch on a minor line (e.g. :0.1)SeeFlow ships with a Claude Code / Cursor / Codex / Windsurf plugin that reads your codebase, understands your architecture, and generates the diagram and request scripts automatically.
Install the plugin and run:
/seeflow show me the shopping cart feature
It scans your routes and database connections, writes seeflow.json, wires up demo scripts, and opens the canvas.
Full installation instructions: https://github.com/tuongaz/seeflow
Content type
Image
Digest
sha256:d7df74e4f…
Size
175.9 MB
Last updated
8 days ago
docker pull tuongaz/seeflow