The Library Was Open The Whole Time

A couple of weeks ago I sat down to do real research with an AI assistant. Not summary work. Not "explain quantum mechanics in three paragraphs." Actual research. I needed papers it could read. By people who exist. Citing other papers that exist.

The standard tools were not getting me there.

What I kept running into was not that the model was not smart. The model is dramatically smart. The model was, structurally, blind. It had been trained on a snapshot of the world from some date in the past, given near-perfect memory of that snapshot, and then forbidden from looking anything up since. Picture a brilliant friend who has read everything ever published, remembers all of it, and has been locked in a room since 2024. You can ask them anything. They will say something. The something will sound right.

The standard response to this is "web search." Web search returns marketing copy. Web search returns SEO summaries of summaries. Web search returns the press release about the Senate hearing, not the transcript. The closest most working researchers will get to a primary source through a frontier model is one of those forty-five-dollar paywall PDFs the model can't actually cross.

We have given the model a library card to a library that doesn't exist.

Here is the part that started bothering me, though. The primary sources are all open. Most of them have been open for twenty years.

arXiv. Europe PMC. The Library of Congress. The US National Archives. UK legislation going back centuries with full historical versioning, which is honestly the kind of public infrastructure most countries do not have. Oxford's institutional repository. Cambridge's. Harvard's. OpenAlex, which indexes 240 million scholarly works on a free public API, a fact I had to stop and reread the first time I came across it. The Smithsonian's catalog holds 14 million records, a number that is meant to make you sit down. NASA's full technical report archive going back to the 1940s. CourtListener's complete corpus of US federal and state case law, which exists, is free, and is queryable in real time. None of which a randomly selected person in legal would necessarily believe if you told them at a party.

That is not a controlled-access world. That is a public library it took us two thousand years to rebuild after the original one burned down.

Nobody had walked an LLM through any of its doors.

So I built it.

It's called Alexandria. It's a Model Context Protocol server, which is the standard adapter the field landed on for letting tools like Claude Desktop talk to external systems without the conversation having to be reshaped around the tool.

The thing exposes seven primitives. The most important is library_ask. You hand it a sentence in plain English. It routes the question to whichever of its 61 sources are most likely to have an answer, queries them in parallel, deduplicates, and returns titles, authors, dates, abstracts, and links to full text.

That is the entire abstraction. It is also the entire point. You should not have to know which library has the thing you need. You need the thing.

The implementation is small. The router is a few hundred lines wrapping gpt-4o-mini against a registry of source descriptions. It picks the five most plausible sources for your query, generates an optimized search string in each one's native language, and dispatches them concurrently. Routing cost is roughly a tenth of a cent. Wall time, under a second. The cost of being wrong, which is most of what makes AI assistants feel haunted, mostly goes away.

Forty-six of the sixty-one sources require no registration. Most of the rest take two minutes to sign up for and cost nothing. The hardest one, BASE, asks you to email the Bielefeld team for IP whitelisting and takes a few days to come back. Email them. Worth doing.

The interesting one is source 61. Google Code Wiki generates live AI documentation for any public GitHub repo on demand. Architecture diagrams, API references, dependency maps. The kind of artifact that usually takes a senior engineer a week to produce, that most projects never get around to. It is indexed. It is excellent. It is also, in the strict sense, not a public API. What it has is the same internal batchexecute RPC protocol that powers Google Maps, Google Search, Google Docs, and roughly every Google product surface you have ever used. I read enough of an existing community wrapper to learn the format, wrote the adapter against the raw protocol, and shipped it. Will it survive an internal Google product decision someday? Eventually no. That is what an MCP adapter is for. When the surface changes, you change the adapter. The user keeps asking questions in plain English.

The library this server is named for was founded in Egypt around 295 BCE, under either Ptolemy I or his son Ptolemy II. The ancient accounts disagree. They agree on this: the Mouseion of Alexandria was unlike anything that had come before it. It was not a repository. It was a research institution built around a universal collection. The explicit ambition was to collect every book in the world. Not books on specific subjects. Every book.

The Ptolemies ran this as state policy. Their agents bought scrolls in the markets of Athens and Pergamon. Ships entering the harbor at Alexandria had their scrolls confiscated, copied, and returned, with the originals going to the Library and the copies going back to the ship. There were customs officials in the third century BCE whose actual job, on the books, included boarding incoming vessels, identifying any scrolls aboard, and taking them. This happened for centuries. The collection at its height was somewhere between 400,000 and 700,000 scrolls. Ancient world's version of a hard number nobody can fully verify.

What happened inside it is what made the institution. Eratosthenes calculated the circumference of the Earth there, to within a few percent. He used sticks and shadows. Euclid wrote the Elements there. Herophilus performed the first systematic human dissections in recorded history there, because the Ptolemies had arranged official permission that nowhere else in the ancient world would grant, which means a noticeable fraction of what we still know about the human body began with a state policy that said yes, you can. Aristarchus of Samos proposed a heliocentric solar system there, seventeen centuries before Copernicus, was widely ignored, and was right. Callimachus produced the first major bibliographic catalog, the direct ancestor of the modern library card system. The Septuagint, the Greek translation of the Hebrew Bible that became the canonical Old Testament for early Christianity, was completed there.

The Library was not a place you went to read. It was the place you went to think, because for several hundred years it was the only place on Earth where thinking at the highest level was structurally possible. Everything you needed was in one building.

Then it wasn't.

The decline was not the single dramatic burning popular history likes to remember. The real destruction was slower and more familiar. Neglect. Political instability. Lost patronage. Funding cuts. A long succession of partial disasters that nobody fully repaired because the institutions that could repair them had stopped having the political capital to bother. The knowledge scattered. Some of it was lost outright. Most of what survived did so in fragments, in copies made before the copies were lost.

What was lost was not just scrolls. It was the original argument for why universal collections matter. The case against centralization is that centralization concentrates fragility. The case for it is that the alternative is every person rebuilding their own library out of whatever they happened to come across in their lifetime, which guarantees redundant effort and missed connections at civilizational scale. The trade-off has not been resolved in two thousand years. What has changed is that the cost of distribution has fallen far enough that we no longer have to pick. The actual canonical sources can live in their institutions. The interface that walks across all of them at once can live anywhere. On your laptop, for example.

Three first-order uses, ordered by ambition.

The first is research that requires primary sources. If the work matters, the abstract doesn't cut it and the SEO summary is worse than nothing. You need the document. The real one.

The second is professional knowledge work where being wrong has a price tag. Legal research where the wrong citation gets sanctions. Medical research where the wrong dosage hurts a patient. Engineering research where the wrong specification produces a recall. All of these benefit from a system that surfaces real sources and refuses to fabricate when it can't find one.

The third is the one I am personally most invested in, which is what happens when a retrieval layer like this becomes one component of something larger.

I have been working on a personal knowledge system. The closest existing vocabulary calls it a "second brain": a structured external memory for everything you have read, written, decided, or wanted to remember. The classic implementation is a closed loop. You put in what you have already collected. You query what you have already put in. It is excellent for what it does. It is also bounded, hard, by the perimeter of your own prior reading. The system gets very good at telling you what you already know. It cannot tell you what you don't.

What an adapter like this changes is that perimeter. The system stops being limited to what you have already encountered. The same conversational interface that lets you query your own notes can reach into 240 million scholarly works, mid-conversation, without you having to leave the chat. A paper that did not exist in your knowledge base ninety seconds ago can be sitting in it now, queryable in the same thread, alongside everything else you have collected. The line between "what I have read" and "what is being published in the relevant field this week" stops being a wall and starts being something the system crosses on your behalf without asking permission.

I am not going to walk you through the specifics of how my own setup works. The architecture decisions are mine and I am still iterating. What I will say is what the effect is. The shift from a closed-loop second brain to one with a live retrieval edge is not a small upgrade. It is the difference between an assistant that knows what you have told it and an assistant that knows what you have told it plus what was published this morning. The first is a personal archive with search. The second feels like a research collaborator who happens to live on your hard drive and does not sleep.

None of this is required to use Alexandria. The server works as a standalone retrieval layer the moment you clone the repository. Most of its value lands without any second-brain plumbing behind it at all. If you already have a personal knowledge base of your own, the integration is a question of pointing the right tools at the right schema, and that is going to look different for everyone. The point is that the option is there. The retrieval layer being open and standardized means anyone building one of these systems gets the same external reach without rebuilding it from scratch.

Server is open source under MIT license at github.com/suavecito585/alexandria-mcp. Clone, build, point Claude Desktop at the compiled binary. Forty-six sources work immediately with no configuration. The fifteen that need keys are tiered in the README in the order you should bother with them. CORE first if you do academic work. Semantic Scholar second. NASA ADS if you're in physics. CourtListener if you're in law. BASE last, because the IP whitelist takes a few days and you'll get plenty out of the other sixty while you wait.

That is the entire setup. Six hours of effort, total, against sources that have been sitting open for twenty years waiting to be assembled in one place.

We have spent those twenty years arguing about whether the model is smart enough. The model has gotten dramatically smarter. The doors to the public archives have changed very little. They were always open. They were never the bottleneck.

It exists now. The library is not on fire. Come in.

Suavecito

Author writes as Suavecito at The 13th Letter. He builds AI infrastructure and releases music. He is not affiliated with any of the institutions whose APIs Alexandria queries. The server is at github.com/suavecito585/alexandria-mcp, MIT licensed.