knowsuchagency

↗ HN profile [ 68.9 ms ] full profile
Karma
0
Created
()
Submissions
305,373,937
  1. Every MCP server injects its full tool schemas into context on every turn — 30 tools costs ~3,600 tokens/turn whether the model uses them or not. Over 25 turns with 120 tools, that's 362,000 tokens just for schemas.…

  2. I built Vibora because I wanted more than a UI to orchestrate multiple Claude Code sessions — I wanted to kick off work, close my laptop, and check progress from my phone while I'm out. You don't need to run it…

  3. The functools.lru_cache (or functools.memoize) function in the standard library is fantastic for what it does. I wrote this library to provide the same interface while allowing the caching mechanism to be any database…

  4. I've been using GitHub Copilot CLI, and while it's great, I found myself wanting something that could work with any LLM (including running local models through Ollama), so I built Skeet. The key features that make it…

  5. Hi HN! I'm stoked to share a project I've been working on called PDF to Podcast. It's a free, open-source tool that automatically converts PDF documents into engaging, informative podcast-style audio content using large…

  6. Hey HN, I've been building quite a few Python services that use LLMs lately. While tools like Magentic and Marvin are great, and served as inspiration for this project, I found myself needing something simpler and more…

  7. Hello HN! LLMO (Elmo) is an AI pair programming tool I created that's become an indispensable part of my workflow. https://github.com/knowsuchagency/llmo LLMO is designed to meet you where you are – your terminal. It…

  8. Hey everyone, So, I stumbled upon this really cool idea of using Pydantic to deserialize and validate OpenAI's outputs over on this HN thread https://news.ycombinator.com/item?id=35821748. It got me thinking about how…

  9. Don't get attached to your code (knowsuchagency.com)
  10. Monads for Mortals (In Python) (knowsuchagency.com)
  11. Collatz Conjecture (journalpanic.com)