Open Compress

Better answers. Faster responses. Lower bills.
Drop-in compression for any LLM, any agent, any gateway.
We only win when you save.

[Open Compress @opencompress_ai]

https://t.co/gk5opJknZc

[Open Compress @opencompress_ai]

@mksglu @chopra_tejas @tirth_8205 @jlehman_ @Nielsen777Brian @harel_nimrod @Compresr_yc_w26 @IvanZakazov @devindolar @janreges @0xnihilism @0xSero @ScryaHQ @bc1beat 🗜️

[Open Compress @opencompress_ai]

https://t.co/gk5opJknZc

[Open Compress @opencompress_ai]

Lots of people asked how we track all these compression projects. We use attentionvc to monitor trending repos by category, super useful for staying on top of the space: https://t.co/e4AI8dj9XL

[Open Compress @opencompress_ai]

@chopra_tejas @bc1beat @mksglu @tirth_8205 @jlehman_ @Nielsen777Brian @harel_nimrod @Compresr_yc_w26 @IvanZakazov @devindolar @janreges @0xnihilism @0xSero @ScryaHQ 100% agree, this is the biggest tradeoff. We actually run cache_stable mode in production for exactly this reason, skip dict and alias stages to keep prefixes deterministic for Anthropic's 90% cache discount.

[Tejas Chopra @chopra_tejas]

Thanks for the mention!

Note - in #headroom, we tried the same techniques - like dictionaries etc - BUT it destroys prefix caching.

So - folks should explore these techniques thinking not just about token compression BUT the impact to prefix caching.

Caching aware compression is key :)

[Open Compress @opencompress_ai]

@wei03_ SQuAD benchmarks don't capture real agent workloads at all. tool output (file reads, grep, test results) is structurally different.

[Open Compress @opencompress_ai]

@mwixamwixa2 and the agent re-reads the same file 3 times and gets the same error in 4 messages lol. paying more tokens for worse output is the real problem

[Open Compress @opencompress_ai]

@Ramdevgujj38411 that's the key question. our take is providers won't prioritize it, charging per token means compression is against their business model. same reason AWS didn't build Cloudflare

[Open Compress @opencompress_ai]

@Shubham75450791 yeah early LLMLingua on code was rough. the key difference is content-aware stages, you can't just drop tokens by perplexity when it's code. AST-aware compression that never touches identifiers is a completely different game

[Open Compress @opencompress_ai]

@lj_xbt Exactly, remove noise on both sides. Input cleaner, output sharper.

[Open Compress @opencompress_ai]

@sukie234 Less token but better quality is the goal

[Open Compress @opencompress_ai]

@Charles_Y_Wu ❤️

[Open Compress @opencompress_ai]

@Tintinx2021 🗜️

[Open Compress @opencompress_ai]

@bc1beat @chopra_tejas @mksglu @tirth_8205 @jlehman_ @Nielsen777Brian @harel_nimrod @Compresr_yc_w26 @IvanZakazov @devindolar @janreges @0xnihilism @0xSero @ScryaHQ love blockrun

[Open Compress @opencompress_ai]

@nikitabier oh i dont think so.