What is hcifootprint?

For decades we designed the interaction between a human and a computer — that's HCI. Now the human isn't alone: an agent joins their side, acting for them. Human and agent, working the computer as a team — that's HACI, and this library is the layer for it.

An agent can already reach your app; the problem is how it operates one. Screenshots are slow and redone every turn, a DOM dump costs ~100k tokens and still guesses, and hard-coded selectors break on the next redesign. A returning human carries a mental model — where things are, what leads where, what they're allowed to do. Your app holds that same map. hcifootprint hands it to the agent as a typed journey graph the agent traverses, with a you-are-here pin so it only ever sees what is actually doable right now.

The key idea, and the reason it's safe to adopt: you are not opening your backend to an agent — you are letting it drive the frontend a human already can. Auth and permissions are unchanged; the agent acts as the signed-in user, through your app's own handlers, and inherits exactly the capability envelope that user already has.

Where to go

• New here? Quick start — author, connect, serve, in three steps that run offline. Then the three contexts, which is how the rest of this site is organised.
• What can this app do? The map — declare it, or grow it from what your app already has: a route table, a journey list, a live action store. Then serve it as one tool per journey or a real MCP server.
• Where am I, and how do I get there? Traversal — one router line, and the declared hops to anywhere.
• What is possible here? Actions — the row a model reads, every stamp on it, and what would free a greyed one.
• Shipping? The drift harness keeps the graph and the app agreeing in CI.
• API surface: the API Reference tab is generated from source on every build — it cannot go stale.

Honest by construction

Everything the runtime derives rather than observes is flagged — guardUnevaluated, activation: 'assumed', toNodeClaimed: true — and every refused action returns a typed reason instead of a success-shaped no-op. That honesty calculus runs through every page of these docs; where a result is a claim, the docs say so.

Also on this site

• The story-deck home — the pitch in three lenses.
• /llms.txt and /llms-full.txt — this documentation as machine-readable Markdown, generated from the same source so it can't drift. (The repo-root llms.txt remains the hand-curated agent front door.)