TristanX
3 things that we are different:
> we calculate user agent:human time leverage (we have a robust mechanism to math that out) > we use linear extrapolation to predict when you will use your usage before reset so you can adjust your pace > we have built out the framework for anyone to grade their coding session history and environment for the indexes they care about with agent skills. i.e. claude.md doctor, comment hygiene, spec drift, subagent cost, etc
Show HN: MemHub, Turn Your GPT/Claude/Gemini History into LLM-Wiki Mindmap
https://github.com/XTraceAI/memhub-llm-wiki-guide
Hi, this is Tristan, CPO of XTrace.We are launching a very cool feature that is inspired by Andrey Karpathy's LLM Wiki mindmap. Let everyone who doesn't have enough sessions and markdowns made with claude code be able to visualize their own memory mindmap!
Show HN: XTrace – Encrypted vector DB (search embeddings without exposing them)
https://github.com/XTraceAI/xtrace-sdk
Hey everyone! This is XTrace. Wanted to share what we’ve been working on for the past year.We built a private vector database from the ground up that performs similarity search on encrypted vectors. The server never sees your plaintext embeddings or documents.The problem we’re trying to solve: every vector DB today requires plaintext on the server. If you're doing RAG over sensitive data...