Open Source Large Language Model (LLM) Tools for Windows

Facilitates local deployment of Llama 3, Code Llama, and other language models, enabling customization and offline AI development. Perfect for creating personalized AI chatbots and writing tools.

An ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

A multi-user ChatGPT for any LLMs and vector database. Unlimited documents, messages, and storage in one privacy-focused app. Now available as a desktop application!.

Alibaba Cloud's general-purpose AI models.

Cherry Studio is a desktop client that supports for multiple LLM providers, available on Windows, Mac, and Linux.

A modern and easy-to-use client for Ollama.

As part of Meta’s commitment to open science, today we are publicly releasing Llama (Large Language Model Meta AI), a state-of-the-art foundational large language model designed to help researchers advance their work in this subfield of AI.

Khoj is an open-source AI second brain that learns from your notes (Obsidian, EMACS), documents, and has access to the internet. It can replace your search engine, help you with reading papers, and get you transparent, fast answers.

Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.

Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!

MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.

Minimal, clean full-stack LLM chatbot, running tokenization, pretraining, finetuning, evaluation, inference, and web UI on a single 8xH100 node.

Visual programming environment for building, debugging, and deploying LLM agent workflows with real-time collaboration, YAML-based version control, and TypeScript integration.

SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters you or the community create.

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, llama.cpp (GGUF), Llama models.

KoboldCpp is an easy-to-use AI text-generation software for GGML models. It's a single self contained distributable from Concedo, that builds off llama.cpp, and adds a versatile Kobold API endpoint, additional format support, backward compatibility, as well as a fancy UI...

Qwen Code is an AI-powered command-line workflow tool designed for developers, adapted from Gemini CLI and optimized for Qwen3-Coder models.

Chat with generative language models locally on your computer with zero setup. LocalChat is a simple, easy to set up local AI chat built on top of llama.cpp. It requires no technical knowledge and enables users to experience ChatGPT-like behavior on their own machines — fully...

NodeTool is a playground for AI that uses a visual canvas to connect different AI tools - like GPT, image creators, and video generators - into one seamless workflow. Instead of jumping between five different apps to write a script, generate an image, and turn it into a video...

LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only call out to a language model, but will also be:

Gtk-LLM-Chat is a graphical frontend for the command-line llm utility. Just as llm integrates large language models into the command line interface, Gtk-LLM-Chat aims to bring that same power to the desktop environment.

The copilot-complete function demonstrates that ~100 lines of LISP is all it takes for Emacs to do that thing GitHub Copilot and VSCode are famous for doing except superior w.r.t. both quality and freedom

llamafile lets you distribute and run LLMs with a single file, providing an OpenAI-compatible API as well as a KoboldAI API.

Council is an open-source platform for rapidly developing customized generative AI applications using collaborating ‘agents’.