Show HN: A MitM proxy to see what your LLM tools are sending • Hacker News Board

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#41

Post by jmuncor » Thu, Jan 29, 2026, 2:37 AM UTC

thehamkercat wrote: post #29

jmuncor wrote: post #23

Earlier quoted context omitted.

Have you tried this with Gemini? or Codex?

Have tried with gemini-cli and claude-code both, it works, honestly, it should work with most if not all cli clients

Working on this feature right now!! Thank you for the suggestion, will start the branch for it... Whent think of improving the context window usage, now that with an http relay we can start thinking of intercepting the context window, anything that you think could be cool to implement?

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#42

Post by jmuncor » Thu, Jan 29, 2026, 2:41 AM UTC

lifetimerubyist wrote: post #39

lmao WTAF is this? build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/build/lib/sherlock

That is what you would call vibe-ception... Hahahahah correcting it now! hahahahahahahaha!!

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#43

Post by vitorbaptistaa » Thu, Jan 29, 2026, 2:56 AM UTC

That looks great! Any plans on allowing exports to OpenTelemetry apps like Arize Phoenix? I am looking for ways to connect my Claude Code using Max plan (no API) to it and the best I found was https://arize.com/blog/claude-code-observability-and-tracing..., but it seems kinda overweight.

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#44

Post by winchester6788 » Thu, Jan 29, 2026, 3:03 AM UTC

interesting that you chose to go the MITM way.

https://github.com/quilrai/LLMWatcher

here is my take on the same thing, but as a mac app and using BASE_URL for intercepting codex, claude code and hooks for cursor.

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#45

Post by winchester6788 » Thu, Jan 29, 2026, 3:05 AM UTC

EMM_386 wrote: post #4

This is great. When I work with AI on large, tricky code bases I try to do a collaboration where it hands off things to me that may result in large number of tokens (excess tool calls, unprecise searches, verbose output, reading large files without a range specified, etc.). This will help narrow down exactly which to still handle manually to best keep within token budgets. Note: "yourusername" in install git clone in…

I had a similar problem, and when claude code (or codex) is running in sandbox, i wanted to put a cap or get notified on large contexts.

especially, because once x0K words crossed, the output becomes worser.

https://github.com/quilrai/LLMWatcher

made this mac app for the same purpose. any thoughts would be appreciated

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#46

Post by cetra3 » Thu, Jan 29, 2026, 3:15 AM UTC

vitorbaptistaa wrote: post #43

That looks great! Any plans on allowing exports to OpenTelemetry apps like Arize Phoenix? I am looking for ways to connect my Claude Code using Max plan (no API) to it and the best I found was https://arize.com/blog/claude-code-observability-and-tracing... , but it seems kinda overweight.

Yeah would love this for logfire

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#47

Post by jmuncor » Thu, Jan 29, 2026, 3:28 AM UTC

jmuncor wrote: post #41

thehamkercat wrote: post #29

Earlier quoted context omitted.

Have tried with gemini-cli and claude-code both, it works, honestly, it should work with most if not all cli clients

Working on this feature right now!! Thank you for the suggestion, will start the branch for it... Whent think of improving the context window usage, now that with an http relay we can start thinking of intercepting the context window, anything that you think could be cool to implement?

Got it on the feature branch http-relay, let me know what you think!

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#48

Post by jmuncor » Thu, Jan 29, 2026, 3:37 AM UTC

the_arun wrote: post #33

I understand this helps if we have our own LLM run time. What if we use external services like ChatGPT / Gemini (LLM Providers)? Shouldn't they provide this feature to all their clients out of the box?

This works with claude code and codex... So you can use with any of those, you dont need a local llm running... :)

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#49

Post by jmuncor » Thu, Jan 29, 2026, 3:40 AM UTC

someguy101010 wrote: post #38

Does this support bedrock?

Could add support if you need it! Just let me know :D

Re: Show HN: A MitM proxy to see what your LLM tools are sending

#50

Post by jmuncor » Thu, Jan 29, 2026, 3:45 AM UTC

cetra3 wrote: post #46

vitorbaptistaa wrote: post #43

That looks great! Any plans on allowing exports to OpenTelemetry apps like Arize Phoenix? I am looking for ways to connect my Claude Code using Max plan (no API) to it and the best I found was https://arize.com/blog/claude-code-observability-and-tracing... , but it seems kinda overweight.

Yeah would love this for logfire

Something like sherlock start --otel-endpoint?