Hermes X-Ray

AIAgentsObservabilityWalkthrough

What does a tool-using agent actually see on each loop?

This is an observability walkthrough of a Hermes-style agent: model-visible context, tool calls, verification gates, and persistence. It is a teaching lab for agent-assisted research, not a live model and not a trading bot.

Technical A standalone HTML, CSS, and JavaScript lab with no backend. It exposes model-visible context, loop stages, tool events, token estimates, verification gates, and persistence boundaries for a Hermes-style agent.

Interact

Go to Page →Open in New Tab →

Source

GitHub →

Demos

Short and full walkthroughs play inline on the project page.

Short demo →Full demo →

Interactive Demo

Standalone observability lab

Send a prompt. Inspect the Hermes runtime path.

Explore prompt intake, context hydration, loop policy, tool dispatch, token estimates, event evidence, verification, and persistence. This HTML/CSS/JavaScript lab is a separate project from Agent Runtime, with its own repository, demo route, and Vercel app.

RuntimeStatic HTML, CSS, and JavaScript

ObservePrompt stack, loop stages, tools, token estimates

Exportsllms.txt · hermes-xray.json

View source on GitHub →Open demo fullscreen →

Video demos