An agent that runs on your premises, and belongs to you.
Age Antique is an AI agent installed on your premises and built on an open or open-weight model, picked from the family that fits your task. You pay for the install once, then a monthly cost close to zero. Your data never leaves and you depend on no one. Installed once, documented, and handed over with its keys.
Intelligence you rent is not yours.
Most companies using AI today do not own it; they have access to it. Every question goes out to an external service, every answer is billed, and the contract that makes all of it possible can change without them.
While usage stays low the question never comes up. It comes up the day the agent becomes a production tool: the cost follows the usage, the documents being processed are yours, and the service stopping stops the work.
Three rules, and not one more.
Everything we install obeys these three rules. They are short because they are checkable: each one can be verified on your own infrastructure.
No trip to a foreign server. The model runs next to your files, inside your network, and keeps going without a connection.
No access key, no subscription someone else can cancel, reprice or read. The day you stop paying us, nothing switches off.
Everything is documented and open: your team can understand it, change it, and swap the model when a better one appears.
What a rented model costs.
The arithmetic is easy and it is rarely done. A service billed per use costs little while usage is low, and its price follows exactly the curve you are hoping for: the more the tool is used, the more it costs. The project succeeding is what drives the bill up.
Then there is what does not show up in the first calculation: your contracts, your customers and your prices pass through infrastructure you do not control, and a change of terms is something you absorb.
- Billed every month, per seat or per token
- Your data flows through the vendor
- Price grows with usage
- Cut off the day you stop paying
- Paid once, at installation
- Your data stays inside your walls
- Monthly cost close to zero, whatever the usage
- Yours forever, even offline
Open models have caught up.
The reason this offer is possible today, and was not two years ago.
Open models have caught up with the closed services on the work an agent actually does: reading a letter, sorting a request, extracting an amount, finding the right document, drafting a reply. Open models, freely published, runnable on hardware you already own, in every family: text, vision, speech, documents, forecasting.
Age Antique installs them on your premises, plugs them into your documents and tools, and hands you the keys. We come back when a genuinely better model appears. Not before.
One agent, its documents, its tools, and the keys.
- The model chosen for the hardware you already have
- Installed on your server or VM, works offline
- Document retrieval over your files, on an open vector store
- Connected to your tools: CRM, ERP, messaging
- Documentation and training so you stay autonomous
- A planned upgrade when a better open model ships
| Workshopworkstation or server with no graphics card | Team32 GB of memory or more | Productiondedicated graphics card | |
|---|---|---|---|
| Text | small model, 1 to 4 B | medium model, 7 to 14 B | large model, 30 B and up |
| Search | multilingual embeddings | embeddings + reranking | embeddings + reranking |
| Vision / OCR | small vision-language | medium vision-language | large vision-language |
| Voice | transcription, synthesis | transcription, synthesis, diarization | real time, diarization |
| Store | open vector store | open vector store | distributed vector store |
Everything is free and open source. Real throughput (tokens per second) is measured on your machine and written into the proposal.
Six weeks, at most.
- Week 1Hardware and use-case audit
We measure your machine, list the documents and tools involved, and pick with you the three tasks the agent takes over first.
- Weeks 1 to 2Model choice and throughput tests
Three open candidates tested on your real documents. You see the answers, response times and memory usage before deciding.
- Weeks 2 to 4Install, RAG and connections
Model, vector store and agent installed inside your network. Hooked up to the chosen CRM, ERP or messaging.
- Weeks 4 to 5Acceptance with your teams
Users test on their real cases. We fix prompts, rules and access rights.
- Weeks 5 to 6Training and handover
Full documentation, training session, upgrade procedure. You are autonomous: the contract ends there.
What we get asked before signing.
What if a better model ships in six months?
What machine do I need?
What about voice and phone?
What happens if Wikolabs disappears?
How much does it cost?
Bring your intelligence home.
Thirty minutes to measure your machine, list your documents and tell you honestly what a sovereign agent can take over for you.