AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Most Markdown editors today assume cloud sync, Electron, or heavy installations. I wanted something simpler. I wanted a Markdown editor that: Works fully offline Opens local .md files directly Saves back to the original file Requires no account, no sync, and no network calls Watch the demo video on GitHub: https://github.com/user-attachments/assets/00d80cbc-ca93-4cfd-86d3-5299895d06b7 So I built
Most coding platforms train engineers to solve isolated algorithm problems. But in real engineering, you rarely reverse linked lists. You debug production systems. You trace issues across files. You deal with incomplete logs, unexpected states, and systems you didn’t write. so I built something around that. Recticode is a platform focused on real-world debugging challenges. Instead of algorithm pu
The Challenge: Beyond the "Lift and Shift" Fatigue The real fear isn’t migration itself—it’s operational fragmentation: different tools, different processes, and different failure modes between the data center and the cloud. After deep-diving into the Nutanix ecosystem, I realized that the goal shouldn't be just moving VMs, but achieving operational symmetry. This is where Nutanix Cloud Clusters
TL;DR macsh is a tiny menu-bar app that mounts SFTP, S3-compatible, and FTP/FTPS servers as native macOS volumes. Open them in Finder, drag files in, edit in place. No macFUSE, no kernel extension, no Recovery-mode reboot. Apache-2.0, free. Heads up: macsh is built with Claude Code. I'm the designer, tester, and maintainer; the implementation is AI-written under my direction. Bugs and decisions
Python has optional type annotations - also called "type hints". Like this: def entry_to_dict(entry: Entry) -> dict: return { 'title': entry.title, 'num_likes': entry.num_likes, 'url': entry.url, } The annotations here being "Entry" as the type for the "entry" argument, and "dict" as the return type. In fact, there are at least 3 ways type annotations can be us
Book: AI Agents Pocket Guide: Patterns for Building Autonomous Systems with LLMs Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub A support agent answers "no, your order shipped on time" with full
Book: RAG Pocket Guide: Retrieval, Chunking, and Reranking Patterns for Production Also by me: Thinking in Go (2-book series) — Complete Guide to Go Programming + Hexagonal Architecture in Go My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabriel.com | GitHub When the embedding API itself collapses, the moments-based detec