Self-hostable AI you can actually run.

Run open LLMs locally via a simple CLI and OpenAI-compatible REST API; pulls and serves GGUF models

C/C++ LLM inference engine for GGUF models, runs on CPU/GPU across platforms

High-throughput, memory-efficient inference and serving engine for LLMs

Desktop app and bindings to run local LLMs privately on consumer hardware

OpenAI-compatible API to run LLM, image and audio models locally, no GPU required

Gradio web UI for running and chatting with local LLMs across many backends

Open-source offline ChatGPT-alternative desktop app running local models

Fast serving framework for LLMs and vision-language models

Apple-silicon array framework for on-device ML including local LLM inference

Distribute and run an LLM as a single cross-platform executable file

Single-file llama.cpp-based runner with a UI for local text and story generation

Hugging Face production toolkit for deploying and serving LLMs

FastAPI OpenAI-compatible server for ExLlamaV2 quantized model inference

Desktop app to discover, download and run local LLMs with a GUI and local server

Small, fast Meta model good for on-device chat and lightweight tasks.

Popular 8B general-purpose model; strong quality-to-size balance.

Strong multilingual 7B model with a permissive license.

Code-specialized 14B model competitive on programming benchmarks.

Google's efficient 9B open model, strong for its size.

Microsoft's compact 3.8B model tuned for reasoning in a small footprint.

Efficient, permissively-licensed 7B model widely used as a local baseline.

Distilled reasoning model that exposes step-by-step thinking, runs locally.

Large 70B model with near-frontier quality; needs a big GPU or lots of RAM.

Self-hosted, feature-rich ChatGPT-like web UI for Ollama and OpenAI-compatible APIs

Modern self-hostable chat UI framework with plugins and multi-provider support

All-in-one desktop/Docker chat app with built-in RAG over your documents

Cross-platform desktop chat client for local and cloud LLMs

Self-hosted multi-model chat UI supporting local and cloud LLM providers

Local frontend for chatting with LLMs, focused on roleplay and character cards

Open-source SvelteKit chat UI that powers HuggingChat, self-hostable with local models

Self-hostable AI suite UI with many models, personas and tools

Native macOS/iOS client for chatting with your self-hosted Ollama models

Desktop app for running local and remote LLMs offline with a polished UI

Self-hostable workflow automation platform with AI/LLM and agent nodes

Visual low-code builder for LangChain-based RAG and agent applications

Open-source LLM app platform with visual workflow, RAG pipelines and agents

Framework for developing applications powered by LLMs, with local model support

Open-source RAG engine with deep document understanding and citations

Fully local RAG API to chat with your documents, no data leaves the machine

Framework for orchestrating role-playing autonomous multi-agent teams

Drag-and-drop builder for LLM chains, agents and RAG flows

Data framework for building RAG and agent apps over your own data

Opinionated RAG framework to integrate GenAI over your files in apps

Open-source AI assistant and RAG search over company docs (formerly Danswer)

Python framework for building production RAG and LLM search pipelines

Open-source RAG UI for chatting with your documents, works with local models

Platform for stateful agents with long-term memory (formerly MemGPT)

Open-source IDE assistant for VS Code/JetBrains, supports local Ollama models

Self-hosted AI coding completion server, a private GitHub Copilot alternative

Autonomous coding agent for VS Code, works with local or cloud models

Terminal-based AI pair programmer that edits code in your git repo

Autonomous coding agent VS Code extension supporting local and cloud models

Autonomous software-development agent platform (formerly OpenDevin)

Free, privacy-focused VS Code copilot designed for local Ollama models

Self-hosted AI coding assistant with completion, chat and fine-tuning

Popular Gradio web UI for running Stable Diffusion image generation locally

Node-graph interface for Stable Diffusion and other diffusion model pipelines

Simplified offline Stable Diffusion image generator with minimal setup

Hugging Face library of pretrained diffusion models for image/audio/video generation

Professional creative engine and UI for Stable Diffusion / diffusion models

Optimized A1111-based WebUI fork for faster local diffusion inference

GUI for training and fine-tuning Stable Diffusion LoRAs and models locally

All-in-one WebUI server for AI image and video generation and processing

Robust open-weight speech recognition and translation model and reference code

C/C++ port of OpenAI Whisper for fast local speech-to-text on CPU/GPU

Deep-learning toolkit for local text-to-speech including XTTS voice cloning

Transformer-based text-to-audio model for local speech, music and effects

CTranslate2 reimplementation of Whisper for faster local transcription

Whisper with word-level timestamps and speaker diarization for local ASR

Fast, local neural text-to-speech optimized for Raspberry Pi and edge devices

Offline speech recognition toolkit with small models for many languages

Lightweight 82M-parameter open-weight TTS model with fast local inference

Flow-matching TTS with high-quality zero-shot voice cloning (weights CC-BY-NC)