Past projects

Every semester, Cogito members build AI projects from scratch – from reinforcement learning and computer vision to LLM agents and robots. Here is a selection of what we have made. All the code is open on GitHub.

TV2 x Cogito

TV2 x Cogito

2024–2026
Collaborations

A multi-semester collaboration with TV 2: machine learning on real article data to understand what engages readers – from engagement prediction to AI-optimized headlines.

Alice Zheng · Afras Mansoor · Olivia Tan · Håvard Fossdal · Folke Jernbert · Kristoffer Nohr Olaisen · Maia Austigard · Sanne Jamila Olsen · Serina Serife Erzengin

Private repo
AIs of Spades

AIs of Spades

Spring 2026
RL & Games

The poker agent UGO learned No-Limit Texas Hold'em by playing thousands of hands against earlier versions of itself. Bluffing was never programmed in – it emerged on its own through reinforcement learning.

Simone Elia · Federico Hrvatin · Even Ytterli Tokle · Miheer Gautam · Daniel Meling

View on GitHub
CancerVision

CancerVision

Spring 2026
Computer Vision

Deep learning that segments brain tumors from MRI scans – separating core, edema and enhancing regions to support diagnostics and treatment planning. AI where it actually matters.

Eldar Alvik · Muhammad H. Muwaffaq · Frida Kroken · Tobias Amundrud · Sofia Kamali

View on GitHub
GymBro AI

GymBro AI

Spring 2026
Computer Vision

The workout partner that never loses count: IMU sensors and pose estimation recognize the exercise, count your reps automatically and give real-time feedback on your form.

Dennis Jevne · Vittorio Avellone · Jens Valderhaug · Gustav Natvig · Ivan Kochura · Henrik Øen

View on GitHub
DeepTactics Arena

DeepTactics Arena

Spring 2026
RL & Games

Chess engines in a duel: AlphaZero and DQN agents trained up and pitted against each other in a shared arena to see which approach wins.

Sverre Nystad · Ludvig Øvrevik · Jessica Liu · Vetle Støren · Håkon Støren · Kristian Flatval · Parleen Brar · Kristoffer Nohr Olaisen

View on GitHub
AI-Driven Stock Movement Predictor

AI-Driven Stock Movement Predictor

Spring 2026
Language & Agents

An agentic AI system that predicts stock movements and makes recommendations – historical data, feature engineering and gradient boosting in practice.

Rasmus Jonssønn Skramstad · Anders Nikolai Holsen · Vegard Aa Albretsen · Aleksandar Mirkovic · Kristoffer Eide

View on GitHub
DeepTactics – TrackMania

DeepTactics – TrackMania

Fall 2025
RL & Games

Self-driving racing: IQN and DQN agents with tricks from the Rainbow and Beyond the Rainbow research, trained to set record lap times on TrackMania tracks.

Ludvig Øvrevik · Brage Kvamme · Edvard Klavenes · Henrik Øen · Simen Førdestrøm Verhoeven · Eldar Alvik · Kristoffer Seyffarth

View on GitHub
Geoguessr AI

Geoguessr AI

Fall 2025
Computer Vision

Show the model a street view image from anywhere in the world, and it answers with coordinates. Deep learning trained to recognize vegetation, road signs and architecture – just like a GeoGuessr pro.

Daniel Neukirch Hansen · Jens Martin Norheim Berget · Magnus Bryne · Sondre Pettersen · Per Henrik Bergene Holm · Parleen Brar · Romeo Henriksen · Håkon Støren · Vetle Støren

View on GitHub
RegulAId

RegulAId

Fall 2025
Language & Agents

The EU AI Act is hundreds of pages of legal text – RegulAId is the agentic assistant that navigates them for you. LLMs and agent technology applied to a problem the entire industry is wrestling with.

Serina Erzengin · Inês Trigueiro · Rasmus Skramstad · Vegard Aa Albretsen · Ingunn Tonetta Erdal

View on GitHub
RizzAI

RizzAI

Fall 2025
Language & Agents

Vision models (BLIP-2) and LLMs in perfect harmony: upload a photo, get a tailor-made pickup line. The science of flirting, served by a vision transformer.

Jozef Kraus · Kristian Carlenius · Christopher

View on GitHub
Norwegian AI Championship 2025

Norwegian AI Championship 2025

Fall 2025
Collaborations

Cogito's official team in the Norwegian AI Championship: computer vision, reinforcement learning and MLOps under competition pressure – and Cogito members took both 1st and 2nd place.

Brage Kvamme · Sverre Nystad · Ludvig Øvrevik · Tobias Fremming · Afras Mansoor · Thomas Sørensen · Serina Serife Erzengin · Mina Al-Dolaimi · Maia Austigard · Jessica Liu

View on GitHub
Grip

Grip

Fall 2025
Robotics & Hardware

A robotic hand that obeys your muscles: EMG sensors read the signals from your forearm, the AI interprets your intention, and the hand grips. Mechanical design, embedded systems and machine learning in one project.

Tobias Fremming · Afras Mansoor · Even Ytterli Tokle

View on GitHub
Cogitron

Cogitron

2019–2025
Robotics & Hardware

Cogito's own robot platform across several generations – firmware, hardware and autonomy built and rebuilt by new cohorts of members.

Christian Gynnild · Dennis Jevne

View on GitHub
Audify

Audify

Fall 2025
Robotics & Hardware

Cogito's exploration of audio and machine learning – signal processing and deep networks meet music.

Sharuca Elangarajah · Muhammad H. Muwaffaq · Nathania Muliawan · Sverre Nystad

View on GitHub
First Steps

First Steps

Fall 2025
Robotics & Hardware

A zbot robot learning to walk in simulation: reinforcement learning in JAX on GPU, from wobbly first steps to a stable gait.

Sebastian

View on GitHub
CogIntro

CogIntro

Fall 2025
Other

The intro group that gives new members a taste of everything: from Git and ML fundamentals via Flappy Bird RL and an LLM chatbot to tumor segmentation on a supercomputer – all in a single semester.

Sveinung Myhre · Maia Austigard · Mina Al-Dolaimi · Kristian Flatval

View on GitHub
DeepTactics – MuZero

DeepTactics – MuZero

Spring 2025
RL & Games

The sequel where the agent isn't even told the rules: MuZero learns its own internal model of the environment and plans inside it. One of the toughest RL algorithms in existence – implemented by students.

Christian Fredrik Johnsen · Ludvig Øvrevik · Eirik Solberg · Kristian Carlenius · Brage Kvamme · Adi Singh · Nicolai André Olsen · Sverre Nystad

View on GitHub
ChessAR

ChessAR

Spring 2025
Computer Vision

AR glasses that recognize the chessboard in front of you and beam grandmaster moves straight into your field of view. So easy it almost feels like cheating – because in a way, it is.

Simon Sandvik Lee · Vetle Støren · Håkon Støren · Alice Zheng · Jessica Liu

View on GitHub
Motion

Motion

Spring 2025
Robotics & Hardware

Real-time motion recognition and interaction, built in C# – your body as the controller.

Tobias Fremming · Maia Austigard · Parleen Brar

View on GitHub
NEATactics

NEATactics

Fall 2024
RL & Games

NEAT is neat! Neuroevolution that doesn't just train the network but breeds the architecture itself – and uses it to play Super Mario Bros.

Christian Fredrik Johnsen · Brage Kvamme · Kristian Carlenius · Ludvig Øvrevik · Kacper Pawlowski · Vetle · Håkon

View on GitHub
CrawlAI

CrawlAI

Fall 2024
RL & Games

Digital creatures learning to walk: agents in a 2D environment evolve body and brain through evolution, one stumbling generation at a time.

Jonas Korkosh · Mina Al-Dolaimi · Nathania Muliawan · Nils Henrik Hoelfeldt Lund · Parleen Brar · Sindre Fossdal · Skage Reistad · Tobias Fremming

View on GitHub
Rubiks Cube Solver

Rubiks Cube Solver

Fall 2024
Computer Vision

From chaos to solved cube: CNNs read the cube, and a combination of graph search, Domino Reduction and classic solving algorithms finds the way home.

Eduard Prokhorikhin · Einride Osland · Even Ytterli Tokle · Gustav Natvig · Kien Le

View on GitHub
J.A.R.V.I.S

J.A.R.V.I.S

Fall 2024
Language & Agents

Just A Rather Very Intelligent System: a voice-controlled AI assistant inspired by Iron Man, autonomously solving complex tasks in the background while you talk to it naturally.

Eldar Alvik · Igor Iwanicki · Jon Bergland · Konrad Seime · William M. Schmidt · Ivan Mordovets · Nils Henrik Hoelfeldt Lund · Erlend Skaarberg · Muhammad H. Muwaffaq

View on GitHub
Hype AI

Hype AI

Fall 2024
Generative AI

A content factory on autopilot: AI generates TikTok videos and publishes them itself – the entire pipeline from idea to uploaded video, with no human in the loop.

Henrik Kvamme · Andreas V. Jonsterhaug · Håvard Daleng

View on GitHub
Cogito x Infor

Cogito x Infor

2024
Collaborations

Cross-sell recommendations and dynamic pricing with embeddings, built together with Infor – the world's third largest provider of enterprise software. Real data, real customers, real value.

Daniel Neukirch Hansen · Thomas Sørensen · Jens Martin Norheim Berget · Bjørn Melaaen · Nikolai Helgås Helleseth · August Myhre · Vebjørn Kittelsen Bergh · Abdihakim Elmi

View on GitHub
DeepTactics – AlphaZero

DeepTactics – AlphaZero

Spring 2024
RL & Games

We took DeepMind's research paper and reimplemented AlphaZero from scratch – policy/value networks, self-play and tree search from the ground up. No off-the-shelf libraries, just papers and PyTorch.

Christian Fredrik Johnsen · Brage Kvamme · Ludvig Øvrevik · Kacper Pawlowski · Kristian Carlenius · Nils Henrik Lund · Haagen Mæland Moe

View on GitHub
Tetris AI

Tetris AI

Spring 2024
RL & Games

Evolution meets Tetris: heuristic agents bred generation by generation with genetic algorithms, until every piece falls exactly where it should.

Eduard Prokhorikhin · Henrik Haaland · Håvard Fossdal · Jon Bergland · Maia Austigard · Øystein Kvandal · Sindre Fossdal

View on GitHub
SudokuSolver

SudokuSolver

Spring 2024
Computer Vision

Point your camera at a sudoku – done. Computer vision reads the board, classic AI search solves it, and the solution is overlaid on the image in real time as AR.

Andreas V. Jonsterhaug · Igor Iwanicki · Afras Mansoor · Lotta Helen Heed Jensen

View on GitHub
Diffusion Model

Diffusion Model

Spring 2024
Generative AI

From pure noise to photorealistic car images, step by step: a diffusion model built from scratch following state-of-the-art research – the same technology that powers Midjourney and Stable Diffusion.

Marijan Soric · Thomas Haslund Wik · Mauritz Skogøy · Amanda Truyen · Baris Batur

View on GitHub
TrainerAI

TrainerAI

Spring 2024
Language & Agents

A personal fitness coach you talk to: the LLM agent logs your workouts, analyzes your progress and builds plans toward your goals.

William M. Schmidt · Tryggve Klevstul-Jensen

View on GitHub
TutorAI

TutorAI

Fall 2023
Language & Agents

Upload an entire textbook and get a personal tutor that knows the syllabus – and cites it. RAG, OCR and function calling in the full-stack app that is Cogito's most-starred repo on GitHub.

Henrik Halvorsen Kvamme · Kaamya Shinde · Kristoffer Nohr Olaisen · Olav Selnes Lorentzen · Parleen Brar · Simon Sandvik Lee · Skage Reistad · Sverre Nystad · Tobias Fremming

View on GitHub
MarketingAI

MarketingAI

Fall 2023
Generative AI

Type in a topic, get a finished poster or meme – image and text generated in one go. Prompt engineering, finetuning and image generation put into a system, long before everyone else did it.

Daniel Neukirch Hansen · Eduard Prokhorikhin · Håvard Fossdal · Jørgen Haugdal Jore · Kristoffer Nohr Olaisen · Olav Selnes Lorentzen · Sveinung Myhre · Sverre Nystad · Simon Sandvik Lee

View on GitHub
Cogito x RBK

Cogito x RBK

Fall 2023
Collaborations

Injury prediction for Rosenborg Ballklub: GPS data from the players' training sessions and matches, analyzed with machine learning to find the patterns that lead to injuries – before they happen.

Erik Nymo Bohne · August Lind · Viktor Grevskott · Lasse Lemka · Daniel Bao Duy Nguyen · Joel Constantions

Private repo
CatMatch

CatMatch

Fall 2023
Computer Vision

Recommender systems meet CNNs: swipe through cats and let the model learn exactly what kind of cat is your perfect match.

Ulrik Røsby · Marijan Soric · Adi Singh

View on GitHub
Doctor AI

Doctor AI

Spring 2023
Computer Vision

Medical image analysis with U-Net: segmentation and classification of real health data using convolutional neural networks – the architecture that revolutionized medical computer vision.

Vilhjalmur Arnar Vilhjalmsson · Sveinung Myhre · Erik Nymo Bohne · Ine Zhao

View on GitHub
Emojify

Emojify

Spring 2023
Language & Agents

An NLP model that reads your text and suggests the emojis to match – language understanding in miniature. 🎯

Ulrik Røsby · Øystein Kvandal · Fredrik Marthin Hellevang

View on GitHub
Cogitopia

Cogitopia

Fall 2022
RL & Games

A world of artificial life and death: agents are born, compete, adapt and die in a simulated ecosystem.

Birk Stoveland · Jonathan Jørgensen · Øystein Kvandal · Albert Bayazidi

View on GitHub
Living Painting

Living Painting

Fall 2022
Generative AI

Generative art that breathes: a painting that lives, moves and never shows the same image twice.

Didrik Lindløv Sand · Espen Boman Fosseide · Ulrik Røsby · Hans Jakob Håland · Ann-Marie Revillard · Magnus Rasmussen · Martin Halleland

View on GitHub
DQN FlappyBird

DQN FlappyBird

Spring 2022
RL & Games

Deep Q-learning teaching itself Flappy Bird – pixels in, flapping out, one frustrating pipe gap at a time.

Sanne Jamila Olsen

View on GitHub
SuperResolution

SuperResolution

Spring 2022
Computer Vision

From pixelated to sharp: deep learning that upscales images and reconstructs details that no longer exist in the original.

Jon Rodtang · Espen Boman Fosseide · Sindre Saastad · Ingeborg Malene Klemsdal · Julie Lervaag Breivik

View on GitHub
AIComposer

AIComposer

Fall 2021
Generative AI

AI that composes music – neural networks learning harmony and melody, creating entirely new pieces.

Theodor Forgaard · Espen Boman Fosseide · Ulrik Isdahl · Mats Ellingsen · Sanne Jamila Olsen

View on GitHub
Bombots

Bombots

Spring 2021
RL & Games

A tournament environment for AI agents inspired by Pommerman: build your bot, drop it into the arena and see if it survives the bombs.

Jonathan Jørgensen

View on GitHub
StyleGAN

StyleGAN

Fall 2020
Generative AI

Faces that never existed: the GAN architecture behind thispersondoesnotexist, explored and trained by Cogito members.

Tobias Christiani · Andreas Gravrok · Espen Boman Fosseide · Henrik Øberg Myhre

View on GitHub
Fake News

Fake News

Spring 2020
Language & Agents

Fake news classification with machine learning – NLP applied to one of the internet's biggest problems, long before LLMs took over.

Espen Boman Fosseide · Birk Stoveland · Einar Sommerfeldt

View on GitHub
AlphaZero

AlphaZero

Fall 2019
RL & Games

Cogito's first encounter with the DeepMind classic: AlphaZero built up from self-play and Monte Carlo tree search, trained to master Tic-Tac-Toe and Connect Four – with zero human knowledge of the games.

Agnar Martin Bjørnstad · Andreas Gravrok · Ole Fredrik Borgundvåg Berg · Sebastian Aas · Tor Dyrdal Strande · Dilawar Mahmood

View on GitHub
DialogFlow

DialogFlow

Fall 2019
Language & Agents

Conversational AI before ChatGPT existed: natural language understanding built with DialogFlow and Kotlin.

Simen Burud · Jakob Madsen · Silas Eic · Marius Torbjørnsen

View on GitHub
Face Aging

Face Aging

Fall 2019
Generative AI

What will you look like in 40 years? Deep networks that age faces – generative AI from the era when GANs were the hottest thing around.

Even Klemsdal · Adam Gaidi

View on GitHub
Vicero

Vicero

2018
RL & Games

Cogito's very own reinforcement learning framework – the foundation many of the later RL projects were built on.

Jonathan Jørgensen · Marius Landsverk · Kim Midtlid · Even Klemsdal

View on GitHub