https://github.com/shobrook/wut
Just type wut and an LLM will explain whatever's in your terminal. You’ll be surprised how useful this is. I use it mainly to understand and debug stack traces, but there are a bunch of other use cases:- Deciphering error codes- Fixing incorrect commands- Summarizing logsYou can connect wut to OpenAI, Anthropic, or a local model via Ollama.I hope y’all find this as helpful as I do!
https://github.com/shobrook/saplings
Hi HN,I built this to address what I see as the fundamental problem with ReAct-style agents: compounding errors. Even a small mistake made early enough in the loop can snowball and ruin the final output. But with search, agents can look multiple steps ahead and backtrack before committing to a particular trajectory. This has already been shown in a few papers to help agents avoid mistakes and...
https://useadrenaline.com/playground
I built this using semantic search and the ChatGPT API, which was just released the other day. What makes it special is it not only understands the code you're debugging, but also pulls in additional context like relevant documentation to help answer your questions and suggest code changes. Ultimately, my goal is to take the hassle out of pasting error messages into Google, finding a vaguely...