The self-hosted stack,
edge to cloud
Agentyk is hosted in the EU, and our language, speech and voice models run on our own servers in the Netherlands: zero-dependency Pure-C engines on a fleet that spans edge devices to multi-GPU servers. Your prompts are processed in the EU.
The Agentyk Inference Engine
English narration, with English captions and Dutch subtitles.
Three Pure-C engines
One zero-dependency runtime DNA for inference, forecasting, and retrieval: small binaries on universal hardware.
Engine
Inference
Runs AgentykLM models on hardware from a Raspberry Pi to a data-centre GPU server, from one small, self-contained binary.
Engine
Forecasting
Runs time-series foundation models at the edge, on the device itself, with the same zero-dependency runtime.
Engine
Knowledge
A vector store and retriever in pure C: the on-device tier of Agentyk Knowledge, running alongside any LLM on any device.
No C++, no external dependencies
Vulkan, Metal, CUDA
NEON (ARM), AVX2, AVX-512
Hundreds of KB, fully self-contained
Kernels tuned per CPU and GPU backend
Nothing to pull at runtime
The self-hosted stack
Open runtimes, our own AI servers, and hosting in the EU.
Runtimes
Open inference engines
Beyond our Pure-C engines, the fleet runs proven open runtimes, picked per model and per box for the best throughput on the hardware it lands on.
Fleet
Edge to data center
A spread of EU-located machines, from low-power edge devices to multi-GPU servers, lets each request run on right-sized hardware instead of one over-provisioned tier.
Self-hosted
Our own AI servers
Our language, speech and voice models run on our own servers in the Netherlands, not on a US cloud. The gateway that routes your requests is hosted in the EU, in Finland.
Reliable
Watched and self-healing
Per-model watchdogs relaunch a down or wedged model automatically, and temperature and health telemetry page on trouble, to keep the lineup up.
Health and temperature, watched continuously
Every box reports reachability, latency, and GPU/CPU temperature on a short interval. Operators see per-box health and temperatures in the admin console, and overheating or a downed model pages the team automatically.
Take charge of your AI infrastructure
Right-sized models and open runtimes, hosted in the EU. Your AI runs on our own servers, not on a US cloud.