Oussama Gabouj is Co-founder and CTO at Compresr (YC W26), an AI infrastructure company that provides LLM-native context compression to reduce token costs and improve accuracy for agents and RAG systems.

Oussama holds a Data Science Masters from EPFL and previously conducted research at EPFL's DLab and AXA, focusing on efficient ML systems and prompt compression.

Oussama is a co-author on multiple research papers in the field of LLM optimization, including work on abstractive prompt compression and generative retrieval-aligned demonstration sampling.

Compresr was accepted into Y Combinator's Winter 2026 batch and has developed both an API for context compression and an open-source compression proxy that works with Claude Code and OpenClaw.

Compresr offers 100x compression rates for LLM context, helping developers reduce token costs while maintaining or improving model accuracy across agentic workflows.