[dead]
Show HN: Context Gateway – Compress agent context before it hits the LLM
71–80 of 89 posts
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#72[dead]
404
Page not found
The page you're looking for doesn't exist or has been moved.
Is this score good or bad? What's the score for the same requests, but without compressor?
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#73[dead]
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#74Earlier quoted context omitted.
How does the model know it needs more context?
Presumably in much the same way it knows it needs to use to calls for reaching its objective.
I'd argue not, as with tool calls it has available to it at all times a description of what each tool can be used for. There's plenty of intermediate but still important information that could be compacted away, and unless there was a logical reason to go looking for it the model doesn't know what it doesn't know.
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#75Earlier quoted context omitted.
We do both: We compress tool outputs at each step, so the cache isn't broken during the run. Once we hit the 85% context-window limit, we preemptively trigger a summarization step and load that when the context-window fills up.
> we preemptively trigger a summarization step and load that when the context-window fills up. How does this differ from auto compact? Also, how do you prove that yours is better than using auto compact?
For auto-compact, we do essentially the same Anthropic does, but at 85% filled context window. Then, when the window is 100% filled, we pull this precompaction + append accumulated 15%. This allows to run compaction instantly
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#76Earlier quoted context omitted.
Subagents do summarization - usually with the cheaper models like Haiku. Summarizing tool outputs doesn't work well because of the information loss: https://arxiv.org/pdf/2508.21433 . Compression is different because we keep preserved pieces of context unchanged + we condition compression on the tool call intent, which makes it more precise.
I can control the model, prompt, and permissions for the subagents. Can you show how your compression differs from summarization by example? What do you mean by "we keep preserved pieces of context unchanged" ?
We keep preserved pieces of context unchanged = compression removes some pieces of the input while keeping the others verbatim. Let us shortly share a concrete example
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#77Swival is really good at managing the context: https://swival.dev/pages/context-management.html
Thanks, checking it out!
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#78I don't want some other tooling messing with my context. It's too important to leave to something that needs to optimize across many users, there by not being the best for my specifics. The framework I use (ADK) already handles this, very low hanging fruit that should be a part of any framework, not something external. In ADK, this is a boolean you can turn on per tool or subagent, you can even decide turn by turn or…
Speaking from experience - serving good context compression is not trivial.
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#79I don't want some other tooling messing with my context. It's too important to leave to something that needs to optimize across many users, there by not being the best for my specifics. The framework I use (ADK) already handles this, very low hanging fruit that should be a part of any framework, not something external. In ADK, this is a boolean you can turn on per tool or subagent, you can even decide turn by turn or…
Speaking from experience - serving good context compression is not trivial.
Ymmv, I don't know why you think it's hard other than you want to sell it
Not my experience
Re: Show HN: Context Gateway – Compress agent context before it hits the LLM
#80Is it all open? Or is compression algo behind a cloud service?