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.
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
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.
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.
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.
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.
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.
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
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
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?
What would you think of simply using an http relay for all providers? Would that make you feel better secutity wise? also could extend the tool to change the context you are sending and make it more granular to what you want/need...
Agee! This was a fun project that I build because it is so hard to understand what "really" is in you context window... What do you mean by plugin/add-on? Add-on to what? Thinking of what to add to it next... Maybe security would be a good direction, or at least visibility of what is happening to the proxy's traffic.
Love you like it!! Let me know any ideas to improve it... I was thining in the direction of a file system and protocol for the md files, or dynamic context building. But would love to hear what you think.
I agree, I remember when the feed forward NN were the shit! And now the LLMs are owning, I think this adoption pattern will start pulling a lot of innovations on other computer science fields. Networking, for example. But the ability to have that peer programer next to you makes it so much more fun to build, when before you had to spend a whole day debugging something, Claude now just helps you out and gives you time to build. Feels like long roadtrips with cruise control and lane keeping assist!
Tried with gemini and gave more headaches than anything else, would love if you can help me adding it to sherlock... I use claude and gemini, claude mainly for coding, so wanted to set it up first. With gemini, ran into the same problem that you did...