Research

We are an AI lab. We build from the ground up and publish openly, always pushing toward AI that is more efficient, more accessible, and safer for everyone.

Read the paper Our GitHub

The lab

We don't adapt. We architect. Every model, every tool, every breakthrough built from the ground up, with your privacy as a fundamental requirement.

Efficiency

Doing more with less. Compact architectures that run on your device without needing a data center.

Accessibility

Open weights, open research. AI that anyone can use, study, and build on, regardless of resources.

Safety

Moderation and alignment research that protects users. Safety systems that work offline, without exposing private data.

Publications

Our work is shared openly so the community can build on it.

May 2026

CosmicFish-HRM

Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

Large language models achieve strong reasoning, though often at the cost of massive parameter counts and expensive inference. We explore a different direction: adaptive reasoning depth in compact language models.

CosmicFish-HRM is built around a Hierarchical Reasoning Module that dynamically allocates reasoning compute during inference. Instead of applying fixed computation to every input, the model iterates through high-level and low-level reasoning cycles and learns when to halt based on input complexity.

Read paper In-depth page GitHub Hugging Face