knrz

https://github.com/CyrusNuevoDia/skill-language-server

I was quite surprised to find no one had built an LSP for agent skills — one where you can go-to-definition, get skill-completions, refactor (and it renames the folder and the name:), so I went ahead and built one!(Reminds me of the old Ruby on Rails days where we had to find-and-replace-all in our codebase to refactor things lol.)Since submitting this on Monday, I've expanded it to provide:-...

https://github.com/CyrusNuevoDia/skill-language-server

https://github.com/cyrusNuevoDia/gpt-workflow

https://github.com/cyrusNuevoDia/capn-hook

https://usesocial.dev

https://www.pgstrata.com/

Photos have pinch-to-zoom; text doesn’t. This is a proof of concept where pinching out compresses prose into a skimmable summary and pinching in expands it back to full detail (and occasionally surfaces a related link). I applied it to PG’s essays as a proof of concept. Would love to see where people take the idea.

https://www.techforiran.com/

https://www.crackedbook.xyz/

https://arxiv.org/abs/2509.05276

https://arxiv.org/abs/2509.04642

https://github.com/zenbase-ai/context42

Show HN: Context42 - AI-powered style guide generator for your codebaseHey HN,I've been building Context42 to solve a problem that's been bugging me: getting AI to write code like me, and helping disseminate coding best practices.The core insight is simple - your existing code is already your best style guide. Instead of debating tabs vs spaces or where to put your curly braces, Context42...

I've been building AI systems for a while and kept hitting the same wall - prompt engineering felt like string concatenation hell. Every complex prompt became a maintenance nightmare of f-strings and template literals.So I built LLML - think of it as React for prompts. Just as React is data => UI, LLML is data => prompt.The Problem: # We've all written this... prompt = f"Role:...

https://jxnl.co/writing/2025/01/22/10-foot-guns-in-fine-tuning-and-few-shots/

https://github.com/shaman-ai/llambdao

Hey HN!This is something that I've been hacking on lately to provide some structure around how we can devise multi-agent LLM architectures. This is a work-in-progress and I'm curious to get y'alls thoughts in this wide open design space :)

https://blog.langchain.dev/unleashing-the-power-of-ai-collaboration-with-parallelized-llm-agent-actor-trees/

https://github.com/shaman-ai/agent-actors

Hey HN! Been working on this library for architecting stateful LLM agent trees that execute in parallel. Think of it like a AI scheduler for BabyAGIs or AutoGPTs, like:-----Parent (Plan and Adjust): Chief Revenue Officer / VP SalesChildren (Do and Check): 3 Sales Development Representatives; 2 Account Managers; 1 Market Researcher.You can give the CRO a task and it will break it down,...