[03] About
Built in Espoo
A Finnish company building the infrastructure for owning your own inferencing.
Infersec is a Finnish company based in Espoo, just west of Helsinki. We build local AI hosting infrastructure — software that turns the hardware you already own into a production-grade, OpenAI-compatible API.
We believe capable AI hardware shouldn't sit idle behind consumer interfaces. It should serve agents, applications and teams the way any cloud provider would — metered, routed and observable — while staying fundamentally yours.
Infersec is founded by Perry Mitchell, a software developer from the Helsinki area. Perry also runs vault.garden, his personal site and digital workshop.
[REGISTRY]
- COMPANY
- Infersec
- LOCATION
- Espoo, Finland
- FOUNDER
- Perry Mitchell
- COORDINATES
- 60.2055°N 24.6544°E
01Can I use my office computer as an LLM source?+
Yes. Install the Infersec conduit on any Linux or macOS machine — mini PCs, desktops, Macbooks, rackmount servers. If it can run an inference engine like llama.cpp or vLLM, it can be a source. Always get the permission of your organisation first.
02Where do models run?+
You can configure models that run on your own hardware, or use hosted models that Infersec provides. In both cases, prompt data never leaves your account and is not used for training purposes.
03What happens when a machine goes to sleep / offline?+
Infersec detects offline sources automatically and reroutes traffic to healthy sources using fallback chains and priority rules. Endpoints stay available even when individual machines drop off.
04What kind of quality / speed can I expect?+
That depends on your hardware and the model you choose. With a modern GPU or Apple Silicon, local models like Llama, Mistral, and Qwen deliver responses competitive with hosted services — often faster since there's no queue behind other tenants.
05Can my Macbook / Mac Studio compete with the big hosted services?+
For many workloads, yes. Apple Silicon handles 7B–70B parameter models well, and Infersec's routing lets you chain multiple machines together. You won't match the largest proprietary models on every benchmark, but for most agent workflows, internal tools, and day-to-day inferencing, your own hardware is more than enough — and you keep full control of the data.
06Can I securely connect my private database to an inference endpoint?+
Yes — Infersec provides server-side tool execution for just this purpose. The LLM will see the database tools within our system, but the actual tool itself does not need to be publicly exposed.