LLM

This GitHub Blog article explains the architecture of today’s LLM applications and ways to begin building one.

LTT Labs publishes hardware test results and analysis for graphics cards, keyboards, mice and power supplies.

Repomix packages local or remote repositories into XML, Markdown, JSON, or text for AI and code review workflows.

Fiddler provides evaluation, monitoring, enforcement, governance, and cost controls for enterprise AI agents.

LLMKube runs self hosted LLM inference across heterogeneous GPU fleets using Kubernetes and several model runtimes.

This article shares practical tips for fine tuning large language models with low rank adaptation, drawn from experiments.

Compose, test, and optimize prompts for language-model applications in Promptmetheus, an IDE supporting more than 100 models.

Use Quarkdown, an open-source Markdown typesetting system, to create papers, presentations, knowledge bases, and static websites.

Harper checks grammar and spelling locally on a device, with an open-source project page for writers and developers.

XAgent supports autonomous complex task solving with a large language model agent.

DeepSpeed provides optimization tools that make distributed deep learning training more efficient.

Gitingest turns a Git repository into a plain text digest designed for use with language model prompts.

GetMarkdown converts PDF, Office files, HTML, images, and audio into Markdown through browser-side file processing.

Magick’s page invites users to create AI agents through its agent building platform.

Neural networks in pure C are provided by notorch, a software library in this repository.

Rapid-MLX is an open-source LLM inference server for Apple Silicon, built on MLX, compatible with OpenAI and Anthropic APIs, focused on reliable tool calling for coding agents.

Subscribe to a uBlock Origin list that blocks websites identified by its maintainer as AI-generated content farms.

Honey reduces token usage by giving AI coding agents a cross-tool skill for writing less code and prose.

PRDKit generates product requirements, user flows, and launch content, then creates related artifacts such as wireframes.

AG2 offers open source tools for building and coordinating AI agent systems.

SoundSwitch switches audio playback and recording devices with a global hotkey, per-app rules, profiles, and notifications.

Agent4Rec implements research on generative agents for recommendation systems.

LiteLLM provides an AI gateway and LLM proxy with model routing, usage tracking, spend controls, and support for many providers.

Microlink SDK provides a Node.js and browser package for screenshots, PDFs, metadata, scraping, and search through its API.