Compresr
ActiveLLM context compression for better accuracy
About
Compresr provides an API that compresses LLM context without losing what matters. It’s a drop-in for agents and RAG that cuts token costs and improves accuracy.
Founders · 4
CEO @ Compresr. Previously researched LLM context compression as an EPFL PhD (Switzerland). Former Microsoft and Philips Research.
CAIO @ compresr.ai. On a mission to make every token count | EPFL CS | prev UBS
Co-founder & COO @ Compresr (YC W26) | EPFL Data Science Masters | ex-Bell Labs
Cofounder and CTO @ Compresr. Previously worked in research at EPFL’s DLab and AXA, focusing on efficient ML systems and prompt compression.
Launch
Cut token spend, reduce latency, boost generation quality.
Compresr offers an API and an open-source compression proxy to reduce long-context in LLM pipelines, enabling 100x context compression to improve generation speed and cost. It targets Claude Code, Codex, and OpenClaw users and promises seamless integration with agentic workflows.
Formerly “Cmprsr”, “compresr”
Related startups
Compression middleware that improves LLM outputs
Systems log compression for agents.
