LLM

A free downloadable guide covering strategies for testing large language models and analyzing their behavior.

shortcast cuts long videos into short clips for TikTok, Instagram Reels, and other platforms through a native macOS app.

This guide explains how to run LLMs locally with llama.cpp across different hardware.

Research on evaluation of LLMs conducted by Microsoft Research and other collaborated institutes. (Updated at: 2023/10).

RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain.

Pipeline Conversations features interviews with platform engineers and machine learning practitioners about MLOps and LLMOps.

Factiverse detects and checks claims across languages and media such as news, audio, and video.

HammerAI offers a desktop app for chatting with AI characters offline using locally run models.

Build AI agents that ship to production. User-scoped execution, rich UI components, and quota management built-in.

MLflow helps teams build AI products by debugging, evaluating, monitoring, and improving AI applications.

WizardLM collects language models developed with Evol-Instruct, including WizardCoder and WizardMath.

The RunAnywhere SDK repository describes a production toolkit for running AI locally.

Google AI documentation shows how to build a durable AI agent by combining Gemini with Temporal.

Calculate language model API costs using input, cached input, and output token counts.

RikkaHub offers an Android interface that supports multiple language models and related LLM services.

A beautiful, cross-platform downloader for YouTube, TikTok, Instagram, and 1800+ sites (yt-dlp GUI) with AI video summaries and post-processing

Run AI agents with OpenFang, an open-source operating system project for agent workflows.

ShellGPT chats with language models in a terminal and can generate shell commands, stories, and Linux-terminal content.

This repository curates platforms, tools, practices, and resources for running language models locally.

SaverTuner extends Android’s built-in battery saver with additional controls.

Alex Smola publishes Adventures in Data Land, a blog with posts on data and related subjects.

Emacs Eat emulates a terminal within an Emacs region, buffer, or Eshell session.

unslop removes stock phrasing and other AI writing patterns while preserving code, URLs, and headings.

Inferable builds AI workflows and agents with human review, structured outputs, and durable execution.