Hacker News: jmuncor

New comment by jmuncor in "Tokentap – Print what your LLM is thinking"

jmuncor — Mon, 06 Jul 2026 20:27:02 +0000

Tokentap is a tool that helps you print the whole context window as you interact with an LLM (Claude, Codex, Gemini, etc). So that you can understand exactly what is going on 'under the hood' of your interaction.

Tokentap – Print what your LLM is thinking

jmuncor — Mon, 06 Jul 2026 20:27:02 +0000

Article URL: https://github.com/jmuncor/tokentap

Comments URL: https://news.ycombinator.com/item?id=48810046

Points: 2

# Comments: 1

New comment by jmuncor in "Local memory for any LLM agent"

jmuncor — Tue, 17 Feb 2026 22:37:23 +0000

This repo is a local database that stores your facts, memories and facts locally so that you centralize everything in your local system. Mumpu - Middleware for Universal Memory Persistence and Understanding

Local memory for any LLM agent

jmuncor — Tue, 17 Feb 2026 22:37:23 +0000

Article URL: https://github.com/jmuncor/mumpu

Comments URL: https://news.ycombinator.com/item?id=47054436

Points: 1

# Comments: 1

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:24:43 +0000

That was what I wanted to answer.. hehe What edge cases can you think of, and what polish do you think I can add?

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:22:56 +0000

Sometimes simplicity is the best thing to have.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:22:11 +0000

Not only trust, but how you later optimize what is in the context to cater how you use llms... There is a whole world to be explored inside that context window.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:20:45 +0000

Thank you, what I was thinking was more along the lines of optimizing how you use your context window. So that the LLM can actually access what it needs to, like a incredibly powerful compact that runs in the background with your file system working as a long term memory... Still thinking how to make it work, so I am super open to ideas.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:18:16 +0000

I love this idea... Going to look into it, thank you!

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:17:11 +0000

Yes, I think you can actually later store this in a database and start querying and optimizing what is happening there. Even you can start using these files or a destilation of these as long term memory.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:15:29 +0000

That is exactly the idea, later we can actually tap into the middle and optimize how the context is actually being used. Feels like the current anthropic tools like compact don't do a great job at it.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:13:18 +0000

You can always try right?

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:12:31 +0000

Yes... Got it patched up and fixed some security issues it had. Let me know what you think of the new version.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:06:54 +0000

Ohh my, no offense taken... The next time I will be a lot more careful with the stuff that I put out there. Learning and getting the hang of it, would love if you either comment on the code or here any other things you think could be improved. I am in the process of getting better and appreciate all the blunt and transparent feedback. No one grows out of praise.

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 07:04:18 +0000

I love the real feedback tbh, I am still learning, and want to learn as much as possible. Would love if you can review it and tell me bluntly either in the repo or here the things that should be improved. I would love to learn more from you and get better :D

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 06:34:30 +0000

Now you can add on top of it :D and we can all create something great :D

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 06:30:37 +0000

Just fixed it and implemented a simple http relay, eliminating the mitmproxy and the ssl_insecure=true. The new implementation uses TLS verification, doing last tests and merging it... After the merge can you check it out and tell me if I earned your star? :D

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 06:08:38 +0000

The idea is to simplify and store it... Thinking of changing it to http relay, what do you think?

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 03:45:57 +0000

Something like sherlock start --otel-endpoint?

New comment by jmuncor in "Show HN: A MitM proxy to see what your LLM tools are sending"

jmuncor — Thu, 29 Jan 2026 03:40:59 +0000

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