Everything that runs on the metal: local model serving behind one OpenAI-compatible endpoint, agents in production, air-gapped reference deployments, and the open retrieval toolchain. Private AI that gives up nothing, proven on our own pair before it reaches yours.
PRIVATE BY ARCHITECTUREEverything that runs on the metal: local model serving behind one endpoint, agents in production, air-gapped reference deployments, and the open retrieval toolchain. Private AI that gives up nothing.
The flagship entry is SparkDuet, the open source operating layer for the two-Spark pair. Its page is the template for every entry that follows.
Four frontier residents on two DGX Sparks: DeepSeek, Qwen 27B, Flash-Next, and GLM-5.3 swap behind one OpenAI port. Weights stay on disk. RAM holds one. On-demand library and QLoRA on the idle node. MIT licensed.
Every client speaks the OpenAI API to one address. Behind it, SparkDuet swaps four residents on the same pair: DeepSeek across both nodes, Qwen 27B as a replica per box, Flash-Next or GLM as a TP=2 swap, plus the on-demand library. RAM holds one resident. The switch is one command.
The same stack runs in the cloud and fully air-gapped. The manufacturing reference deployment runs six local models, offline retrieval over 765,000 chunks, and 57 tools with zero external dependencies: the whole capability, not a reduced mode.
Models, retrieval, and agents running on hardware you control: the Lab's own two-Spark pair in daily operation, and client deployments up to fully air-gapped. The same stack runs in the cloud and offline; environments where data cannot leave the building get the whole capability, not a reduced mode.
DeepSeek-V4-Flash, Qwen 27B, Qwen3.8-Flash-Next, and GLM-5.3-Flash swap on the same two Sparks behind one OpenAI-compatible endpoint. Smaller models and the Lab's own fine-tunes still load on demand. One command switches the resident.
Yes. The reference case is a manufacturing deployment with six local LLMs of about 58 GB, a 765,000-chunk offline retrieval corpus, and 57 callable tools, entirely behind the plant firewall with zero external dependencies.
The Lab does, around the clock: the Hermes agent series documents the full path from install to production on local vLLM-served models, including tool permissions, security hardening, a Telegram gateway, scheduling, and memory, in eighteen posts.
The open toolchain: DocPrep-AI prepares enterprise documents for retrieval entirely in the browser, Weaviate Local UI makes local vector data inspectable and queryable, and the retrieval engineering posts document the failure modes in between. All open source under github.com/zorost.
We don't pitch slide decks. We show you what we've already built in your domain, then engineer what your mission requires.
