Compass Labs
Automated Decision-Making for Decentralized Systems
Compass Labs accelerates the adoption of blockchain technologies by building the AI infrastructure to automate and optimize user interactions with any blockchain system. In doing so, we bring together a team of experts in developing and deploying cutting-edge machine learning solutions to the decentralized space.
On-chain Simulation Environments
Compass Labs leverages the open-source nature of the blockchain to build extremely realistic simulation environments for DeFi.
We train autonomous agents to optimize and automate user interaction, and discover opportunities at scale.
Our product is currently in closed alpha version.
RAW
Dynamic liquidity provisioning on Balancer
through rebalancing asset weights.
Coming soon
Minimised
Impermanent Loss
Rebalancing asset weights enables reduces impermanent loss without
active management
Socialized
Gas Costs
Gas fees are socialized across the
entire RAW pool to make active liquidity provisioning economical for all
Research
At Compass Labs we collaborate with top academic institutions to contribute to research
at the intersection of mathematical finance, statistics, machine learning, and crypto to
improve our products and find opportunities in key areas of decentralised finance.
A framework to generalize impermanent loss for
multiple asset pools obeying any constant function
market maker with optional concentrated liquidity.R. Tangri, P. Yatsyshin, E.A. Duijnstee, D. Mandic
Team
We are a technology startup with engineers and academics with years of experience in computational simulations, machine learning, statistics, finance, infrastructure and crypto.Great people make great things happen! If you find our projects exciting, we'd love to hear from you 💬

Elisabeth Duijnstee
Co-Founder & CEO
Ph.D. in Physics @ University of Oxford
Machine Learning fellow @ Faculty AI
Founders and Funders @ Oxford's Business School

Rohan Tangri
Co-Founder and CTO
Ph.D. in Statistical Machine Learning @ Imperial College
AI/ML team @ JP Morgan
Algorithms @ NASA's Mars Mission

Peter Yatsyshin
Research Scientist
Ph.D. in Statistical Physics @ Imperial College
Research Fellow @ Alan Turing Institute
Research Fellow @ Imperial College