Le Space Automation

Compute and data, back in-house

That is the core of local-first peer-to-peer, and it is our programme of work: the data stays with the company and is processed where it resides — on its own devices, not on someone else's servers. Team and business partners receive it directly, device to device; a relay brokers at most the connection, never the content. And archiving happens continuously, with every change, rather than in a backup window at night: encrypted, preferably on decentralised storage — and, on request, as a second copy with a classic cloud store such as Amazon S3, Google or Azure.

The principle behind it fits in one sentence: compute returns in-house, and outside the house only ciphertext exists — regardless of whether it is hosted centrally or decentrally. The one exception we name explicitly: the language model. It runs locally or with a provider of your own choosing and receives only what is handed to it redacted.

The signs are changing

Standard software had an economic rationale, not a functional one: custom development was too expensive, and running it for years more expensive still. For two generations, companies therefore struck the same compromise, first with the purchased licence, then with the cloud subscription: the organisation adapts to the software, not the software to the organisation. Renting did not resolve that compromise; it made it permanent.

What is changing now is the cost side of that calculation. With AI agents, what used to bind months is built in days, and maintenance, until now the decisive item against custom software, turns from the exception into routine. That moves the threshold at which a solution of your own pays off, and it moves in one direction: not every cloud tool is replaceable tomorrow, but the set of what sustains itself as an in-house solution grows every month.

Two arguments remain that appear in no cost calculation. With rented software your data sits with third parties, often in a foreign jurisdiction; every data-protection review thereby becomes a review of a supply chain. And the bargaining power lies with the provider: if it raises prices, retires the product or is sold, you negotiate without your software and with your data in its hands.

“Data is safer in the cloud” — true against the laptop, and against a server of your own

The second argument for rented software was safety: backups, redundancy, an operations team. Fair — against a single laptop, and just as fair against the server in the back room: small and large companies alike moved it to the cloud because patching, backups and round-the-clock duty were not their business. We do not bring that server back. With us, local does not mean one device but all of yours: they carry the same data and reconcile among themselves, with no server in between. And every change travels encrypted into a decentralised archive, from which a new device gets everything back with your passkey. That is the data centre's redundancy — only nobody but you holds the key. Today the archive sits encrypted on Aleph Cloud; Filecoin Onchain Cloud and Lighthouse are in the works. And whoever wants it gets a second copy with a classic host — Hetzner, Amazon, Google, Microsoft —, built on request, ciphertext there too: the provider holds a copy it cannot read.

The cloud, by contrast, is a honeypot: one breach at the provider hits every customer at once, and the provider sees everything in the clear. That place does not exist with us — no server, no password, only ciphertext in the archive. What remains is your device; you protect it with rented software just the same, because that is where the browser runs your session.

Said honestly: this holds once a second device or the archive is set up — a single laptop without an archive is as vulnerable as ever. Which is why archiving is part of the set-up with us, not a pro tip. And you keep browser and operating system current yourself; we patch no servers, because there are none.

What we automate

• Receipt flow and pre-accounting — with Le Space Belege as a ready building block: collect receipts, match payments, hand over the DATEV package
• Quotes and invoicing, with payment matching
• Post and mail intake: sort, extract the data, file, draft replies — never sent unchecked
• Data transfers between systems that do not know each other: CSV, interfaces, portals
• Recurring reports and evaluations
• Replacing single subscription tools with a tailored tool of your own

How the agents work

• Agents write and maintain the code; people set the goals and check every result. We answer for what runs — not the model.
• Every change lives versioned in Git: traceable, revertible, with its reason.
• Automated tests are the net: whatever the agents change has to prove nothing breaks before it reaches you.
• Open source wherever possible — checkable instead of taken on trust. The value is not in the code but in it running, and in someone standing behind it.
• Your model, not ours: the AI runs locally or at a provider of your choice, and your data stays in house — as with Le Space Belege.

Step by step, not big bang

We start with one process, not your whole IT. The current solution keeps running alongside until the new one has proven itself in daily use — only then is the next process due. And you can cancel without loss: if you cancel us, you keep the software, the source code and your data. With a subscription you keep an export file.