Verdichtung is German word that loosely means “densification”. It represents an alternative to urban sprawl⁰ that is prevalent in US cities and has been the dominant strategy for Zurich’s expansion.

An offline macOS music player. Contribute to kushalpandya/Petrichor development by creating an account on GitHub.

I came up with these little spinning doodads a few years ago around Christmas, and I haven’t seen anything like them online, so I’m writing about them here as they are quite fun to make. I’ve just been calling these things “can spinners” (ChatGPT suggested “twirluminum”).

Production-ready platform for agentic workflow development. - langgenius/dify

Easy Data Preparation with latest LLMs-based Operators and Pipelines. - OpenDCAI/DataFlow

Discover the first portable Wi-Fi 7 travel router, offering speeds up to 3600 Mbps. Perfect for travel, business, and families needing reliable connectivity.

Convert HTML and CSS to high-quality PNG images instantly. Perfect for dynamic OG images, social shares, and automated screenshots.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management. - Agent-Skills-for-Context-Engineering/skills/project-development at main · muratcankoylan/Agent-Skills-for-Context-Engineering

This skill covers the methodology for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development. The principles apply whether building batch processing pipelines, multi-agent research systems, or interactive applications.

Analyzing Hacker News discussions from a decade ago in hindsight with LLMs - karpathy/hn-time-capsule

A Hacker News time capsule project that pulls the HN frontpage from exactly 10 years ago, analyzes articles and discussions using an LLM to evaluate prescience with the benefit of hindsight, and generates an HTML report.

A Model Context Protocol (MCP) server that facilitates structured, progressive thinking through defined stages. This tool helps break down complex problems into sequential thoughts, track the progression of your thinking process, and generate summaries.

Using LLMs to identify extraordinary prescience, confident delusions, and the madness of earnings calls. Inspired by Andrej Karpathy

Auto-Grading Ten Years of Earnings Calls for Prescience and Delusion

Earnings Call Civilizational Score Prompt. GitHub Gist: instantly share code, notes, and snippets.

You are a financial historian and industry expert conducting a review of past earnings calls with the benefit of hindsight and wisdom.

In-depth tutorials on LLMs, RAGs and real-world AI agent applications. - ai-engineering-hub/fastest-rag-milvus-groq at main · patchy631/ai-engineering-hub

This project builds the fastest stack to build a RAG application with retrieval latency < 15ms.

It leverages binary quantization for efficient retrieval coupled with Groq’s blazing fast inference speeds.

We deliver inference with unmatched speed and cost, so you can ship fast.

PartyKit now includes a vector database and access to an embedding model. Here’s a guide on how to use them to build a search engine.

The tl;dr is that search got really good suddenly and really easy to build because of AI.

An Open Source implementation of Notebook LM with more flexibility and features - lfnovo/open-notebook

AI writing agent powered by gemini 3 flash - autonomously creates novels and stories with deep reasoning

An autonomous agent powered by Google’s Gemini 3 Flash model for creating novels, books, and short story collections.

Features 🤖 Autonomous Writing: The agent plans and executes creative writing tasks independently 📚 Multiple Formats: Create novels, books, or short story collections ⚡ Real-Time Streaming: See the agent’s thinking and writing appear as it’s generated 💾 Smart Context Management: Automatically compresses context when approaching token limits 🔄 Recovery Mode: Resume interrupted work from saved context summaries 📊 Token Monitoring: Real-time tracking of token usage with automatic optimization 🛠️ Tool Use: Agent can create projects, write files, and manage its workspace 🧠 Advanced Thinking: Uses Gemini’s thinking mode for better reasoning

What you need to know about local model tooling and the steps for setting one up yourself