Compresr (YC W26) (@cmprsr) header
Compresr (YC W26) (@cmprsr) profile picture

Compresr (YC W26)

@cmprsr

Research-backed context compression for LLM agents. Reduce token usage by up to 90% without losing semantic meaning.

 San Francisco
compresr.ai
Joined January 2026
  • Tweets7
  • Following12
  • Followers60
2Media
Photo by Compresr (YC W26) (@cmprsr)Photo by Compresr (YC W26) (@cmprsr)
Compresr (YC W26) retweeted
Ivan Zakazov (@IvanZakazov) profile picture
Ivan Zakazov
@IvanZakazovAug 20
Replying to @cmprsr
@cmprsr is hiring a research intern - come optimize agent context with us!
Image from Ivan Zakazov (@IvanZakazov)
2
1
7
437
Image from Compresr (YC W26) (@cmprsr)
1
3
547
with me they'd already be engaged!
Image from Compresr (YC W26) (@cmprsr)
3
147
Compresr (YC W26) retweeted
Ivan Zakazov (@IvanZakazov) profile picture
Ivan Zakazov
@IvanZakazovMar 8
Replying to @KamelCharaf
@KamelCharaf and I at 4am: wanna record a proxy demo for the PH launch? 😂 claude code just works better with @Compresr_yc_w26 proxy
1
1
2
311
Compresr (YC W26) retweeted
Ivan Zakazov (@IvanZakazov) profile picture
Ivan Zakazov
@IvanZakazovMar 6
We built a proxy that compresses Claude Code/OpenClaw tool outputs before they hit the model. We're now live on Product Hunt! Fighting context bloat since 2026 👉👈 producthunt.com/products/con…
Context Gateway: Make Claude Code faster and cheaper without losing context | Product Hunt

Context Gateway: Make Claude Code faster and cheaper without losing context | Product Hunt

Context Gateway cuts latency and token spend for Claude Code / Codex / OpenClaw by compressing tool output while preserving important context. Setup takes less than a minute. Quality-of-life featur...

producthunt.com
4
3
15
873
Load more