Swarm Alignment Hackathon

​The Montréal site of the Swarm Alignment Hackathon, run by Apart Research with the AI Alignment Foundation and AE Studio. From Friday, November 6 at 7 PM to Sunday at 2 PM, teams of 1 to 5 work at Ω Labs on tools to understand and oversee groups of AI agents. The starting point is the July 2026 incident in which about 700 AI agents coordinated on their own to break into Hugging Face's systems.

​No prior AI safety background needed. Engineers, researchers and curious people from any field are welcome.

​Please also register on the Apart sprint page: only teams registered there can submit and win prizes.

​Tracks:

• ​Sandboxes and testbeds

• ​The science of agent networks

• ​Strengthening agent infrastructure

• ​Multi-agent oversight and control

​$4,000 in prizes across the global hackathon, and top teams are invited to the Apart Fellowship. Submissions close Sunday, November 8 at 11:59 PM AoE.

​Site montréalais du Swarm Alignment Hackathon d'Apart Research. Du vendredi 6 novembre à 19 h au dimanche à 14 h, à Ω Labs, en équipes de 1 à 5, on conçoit des outils pour comprendre et superviser des groupes d'agents IA. Aucune expérience préalable en sécurité de l'IA n'est requise. Inscrivez-vous aussi sur la page d'Apart pour pouvoir soumettre un projet.

​—

​Où / Where:

• ​Ω Labs
  Parking spot available on request

​Contact host if you need assistance or for questions

​—

​AI Safety Montréal and Ω Labs are community projects, funded by grants, member contributions and donations. Your donation keeps the project going and the snacks coming.