Canonical: https://northloom.ai/products/

ProductsThree independent systems

# Tools for the work around AI.

Running models is only one part of putting AI to work. Companies also need secure software, dependable context and clear control. We build products for each layer.

01

Open-source inference runtime

Northloom product

## Krasis

### Run larger models on the hardware you already understand.

Krasis lets system memory work alongside Nvidia VRAM, so a model does not have to fit entirely on the GPU. It gives smaller teams a viable way to serve much larger models without moving straight to multi-GPU infrastructure.

* Free and open source
* Native Linux and Windows support
* Nvidia hardware
* Public repository with hundreds of stars
[Visit krasis.ai↗](https://krasis.ai/)

01**K**

02

Always-on source-code security

Northloom product

## Dokima

### Find vulnerabilities as the codebase changes.

Dokima continuously scans source code and produces clear vulnerability reports. Security review becomes part of the normal life of the codebase, rather than a separate exercise that happens after the work is done.

* Continuous source-code scanning
* AI-assisted analysis
* Actionable vulnerability reports
* Built for active codebases
[Visit dokima.net↗](https://dokima.net/)

02**D**

03

AI control plane

Northloom product

## Lore

### Give every agent the right context and the right limits.

Lore connects private AI workspaces to a permissioned repository of organisational context. Leadership can set policies that reach every agent, while teams manage the work, context and instructions that belong to them.

* One or many private AI workspaces
* Shared, permissioned company context
* Organisation-wide policy
* As many specialised agents as you need
[Visit lore.tools↗](https://lore.tools/)

03**L**

Need help choosing?

## The products are independent by design.

Each has its own website, billing and sales model. Start with the operational problem you need to solve.
