Skip to main content
The demo runs on your machine: a FastAPI backend streams events over WebSocket, and a Next.js frontend displays the graph, decisions, event log, and metrics. Start with exact; it needs no provider credentials.

​
Set up the checkout

You need Python 3.11+, pip, Git, and Node.js with npm. The UI uses Next.js 16; use a supported Node.js version for that release.
Activate the environment:
Install the source checkout and demo dependencies:
The base PyPI install doesn’t include the backend, model SDKs, or frontend. requirements.txt is another supported source-demo installation path.

​
Choose an offline or provider-backed run

For exact, leave credentials unset. For other scenarios, create a root .env file using .env.example as a starting point:
Choose a provider configuration in .env:
The demo chat-model default is gpt-4o-mini. LOOPGUARD_OPENAI_MODEL overrides it.
Set both provider selectors explicitly. The embedding library defaults independently to OpenAI, even if the chat-model selector is Gemini. Restart the backend after editing .env; existing process environment values take precedence over the file.
semantic needs embeddings but no chat model. controlled_progress, controlled_503, and controlled_401 need a chat model but no embeddings. controlled_empty, calc, and trap need both. Provider-backed runs may incur API charges; the trap scenario also performs real web searches.

​
Start the backend

In a terminal at the repository root with the Python environment active:
Check http://localhost:8000/runtime to see the selected providers and chat model. This endpoint does not test credentials or model access.

​
Start the frontend

In a second terminal at the repository root:
Open http://localhost:3000. Choose Scripted: identical tool loop, then select Run. Watch repeated empty results build evidence until the run stops.
LoopGuard demo main interface with an agent-tool graph, repeated tool observations, and metrics

The graph, event log, and metrics show a stuck LoopGuard demo run.

​
Change the backend address

The frontend defaults to http://localhost:8000 and derives the WebSocket address from it. To use a different backend, set NEXT_PUBLIC_LOOPGUARD_API in ui/.env.local, then restart the frontend:
The browser must be able to reach that address. See connection troubleshooting.

​
Use the terminal instead

With the Python environment active, from the repository root:
The backend and browser use the same scenario definitions as this CLI. See demo scenarios for expected behavior and provider requirements.