Kamel Charaf is Co-Founder and COO at Compresr, a Y Combinator W26-backed company building LLM-native context compression technology. Compresr provides an API that compresses LLM context without losing critical information, offering 100x compression for AI agents and RAG systems.

Kamel earned a Data Science Masters from EPFL and previously worked at Bell Labs, where he focused on research in efficient ML systems. He has published research on anomaly detection and machine learning methodologies.

Kamel brings deep technical expertise in data science and machine learning from his time at EPFL and Bell Labs. His work has contributed to advancing efficient ML systems and prompt compression techniques.

Compresr is part of Y Combinator's Winter 2026 batch and has developed an open-source compression proxy that optimizes context for AI coding assistants like Claude Code. The platform cuts token costs while improving accuracy for AI agents and RAG applications.

Compresr's technology enables 100x context compression, helping developers reduce LLM costs and improve performance. The company's open-source tools integrate seamlessly with popular AI development workflows and take just minutes to set up.