Aleph Alpha's open-weight reasoning model, built and trained in Europe: 78B mixture-of-experts with 3.5B active, German and English, up to 1M tokens of context, Apache 2.0.

TypeSafe AI's Jev decides instead of writing: a typed answer with a probability in about 150ms, where an LLM takes seconds.

One API key and one bill for 458 AI models from 63 labs, with automatic fallbacks when a provider fails. Model prices pass through, and OpenRouter takes 5.5% on credit purchases.

Training a small model to write in my voice, wired behind a frontier model that does the thinking. When it beats prompting, and what it costs.

Rust CLI that reads your hardware and ranks which local LLMs will actually run on it, with a TUI, a web API and community benchmarks.

The LLM-maintained wiki pattern (after Karpathy), and how I turned it into a working skill that ingests my files nightly and keeps a cross-linked knowledge base current.

Google's Python library for extracting structured data from unstructured text using LLMs with source grounding.

AnythingLLM is an open-source, all-in-one AI desktop app that bundles RAG, AI agents, document chat, and multi-model support into a single privacy-first package.

code-generated diagrams

ai, llm

in the AI age, everything should have its .md version

Overview of the Ollama Python library for running and interacting with large language models locally.

framework for developing applications powered by language models

LLMs are the new hot thing.