Canonical: https://northloom.ai/

Northloom / Applied AI01—26

# AI tools built for _real organisations._

We build products that help companies run capable models, secure their software and coordinate AI agents across their organisation.

[Explore our products↗](https://northloom.ai/products/)[Self-hosted AI consultancy](https://northloom.ai/consultancy/)

Multiple productsOne focus

![Northloom mountain mark](https://northloom.ai/assets/nl_logo_notext.png)

[01**Krasis**Run](https://krasis.ai/)[02**Dokima**Secure](https://dokima.net/)[03**Lore**Coordinate](https://lore.tools/)

Independent products. Built around work companies are doing now.

What we build

Useful infrastructure at the point where AI meets **people, software and hardware.**

Products / 03

## Built for work,  
not demonstrations.

Each product solves a distinct operational problem. Each is available independently, with its own website and delivery model.

01

Open-source inference

### Krasis

Run models beyond the capacity of your GPU. Krasis uses system memory alongside Nvidia VRAM to make larger models viable on accessible hardware.

Free to use · Linux and Windows · Nvidia

[↗](https://krasis.ai/)

02

Always-on code security

### Dokima

Dokima continuously scans source code and reports vulnerabilities. Your team sees risks as the codebase changes, not weeks after a scheduled review.

Continuous source-code analysis

[↗](https://dokima.net/)

03

AI control plane

### Lore

Give agents shared context, organisational policy and clear permissions. Teams can create as many specialised agents as their organisation needs.

Private workspaces · Shared context · Policy

[↗](https://lore.tools/)

Measured work

## Large models.  
Accessible hardware.

Krasis makes it possible to run capable models beyond GPU memory limits. These are measured inference results from single-GPU systems.

[See the technical work↗](https://northloom.ai/technical-work/)

Ornith 397B

Krasis / single GPU

**2,354**tokens/sec prefill

**25.72**tokens/sec decode

1× RTX PRO 6000 · 96 GB VRAM · 200 GB DDR4

Northloom / Inference![](https://northloom.ai/assets/nl_logo_notext.png)

Private AI consultancy

## Private AI. Practical expertise.

Choose models, plan GPU hardware and understand inference performance. Our senior engineers help you make informed decisions, with clearly scoped assessments and ongoing advice. Your team keeps control of the systems.

* Infrastructure planning · £1,750
* Model & performance assessments
* Technical adviser · from £1,750/month
[Explore services and pricing ↗](https://northloom.ai/consultancy/)

20+

Experience

## Built by people who have spent more than two decades running software companies.

We favour clear engineering, measured results and products that earn their place in an organisation.
