docker compose up -d
Self-Hosted AI and LLM Tools
Run models on your own GPU. Local large language model runtimes, chat front-ends, and image generation interfaces that keep prompts and documents off third-party APIs.
28 apps in this category
AnythingLLM: Chat With Your Own Documents An all-in-one RAG application that ingests documents into workspaces, embeds them into a vector database, and answers questions with citations, using local or hosted models.
ComfyUI: Node-Based Stable Diffusion Interface A powerful, modular diffusion model GUI with a node-based graph interface, plus an API and backend for running image and video generation entirely on your own hardware.
Dify: Building LLM Applications Without Writing the Plumbing A platform for building AI applications with a visual workflow editor, RAG pipeline, agent tooling, and prompt management, exposing what you build as an API.
Flowise: Drag-and-Drop LLM Workflows A visual builder for chaining language models, retrieval, and tools into working applications, with the result deployable as an API or an embeddable chat widget.
InvokeAI: A Refined Interface for Stable Diffusion A creative tool built around a unified canvas for generating and editing images locally, with node-based workflows available underneath for people who want them.
Jan: A Local-First Desktop AI Assistant An open-source desktop application for running language models locally, with a familiar chat interface, a model hub, and an OpenAI-compatible local API server.
Khoj: A Personal AI That Searches Your Own Notes Connects a language model to your documents, notes, and email so you can ask questions about your own material, with support for Obsidian, Notion, and local files.
Langflow: Visual Flow Building With a Python Escape Hatch A low-code visual editor for language model pipelines where every node is a Python component you can edit, bridging the gap between drag-and-drop and writing code.
LibreChat: One Chat Interface for Every Model A ChatGPT-style web interface that talks to OpenAI, Anthropic, Google, and local models through Ollama, with multi-user accounts, conversation search, and per-user API budgets.
LibreTranslate: A Self-Hosted Machine Translation API An open source translation API and web interface powered by Argos Translate models that runs fully offline, with file translation, API keys, and optional GPU acceleration.
LinguaCafe: Self-hosted software that helps language learners Self-hosted software that helps language learners acquire vocabulary through reading.
llama.cpp: The Inference Engine Under Most Local AI A C++ implementation of language model inference that runs on CPUs, consumer GPUs, and Apple Silicon, and quietly powers a large share of the local AI ecosystem.
LobeChat: A Polished Chat Interface With a Plugin Ecosystem A modern chat front-end supporting many model providers, with a plugin marketplace, custom assistants, voice input, and multimodal support, deployable as a container or to the edge.
LocalAI: A Drop-In OpenAI API for Your Own Hardware A local inference server that implements the OpenAI API specification, so existing applications point at it with a URL change and get chat, embeddings, audio, and image generation locally.
Ollama: Run Language Models Locally A tool for running large language models on your own hardware with a single command, exposing an API compatible with many front-ends.
Onyx: Search and Chat Across Your Team's Tools Formerly Danswer, an open-source enterprise search platform that connects to Slack, Confluence, Google Drive, GitHub, and dozens of others, then answers questions with citations.
Open WebUI: Self-Hosted AI Chat Interface A polished, self-hosted chat interface for Ollama and OpenAI-compatible APIs, with multi-user support and RAG built in.
Perplexica: A Self-Hosted AI Search Engine Combines a language model with live web search to answer questions with cited sources, running entirely on your own infrastructure using SearXNG and a local model.
Piper: Fast Local Text to Speech A neural text-to-speech system optimised to run on modest hardware including a Raspberry Pi, with natural-sounding voices in many languages and no network dependency.
RAGFlow: Retrieval Built Around Document Understanding A RAG engine that puts unusual effort into parsing documents correctly, handling tables, layout, and scanned pages, on the argument that retrieval quality starts with extraction quality.
SecureAI Tools: Private and secure AI tools for everyone's Private and secure AI tools for everyone's productivity.
Speaches: An OpenAI-Compatible Speech-to-Text and Text-to-Speech Server Self-hosted speech API with OpenAI-compatible endpoints: transcription and translation with faster-whisper, and speech generation with Piper and Kokoro, on CPU or GPU. Described as Ollama for speech models. MIT.
Stable Diffusion WebUI: Local Image Generation The AUTOMATIC1111 web interface for Stable Diffusion, giving local text-to-image generation with inpainting, upscaling, ControlNet, and an extension ecosystem.
Subvert: Generate subtitles, summaries, and chapters from videos in seconds Generate subtitles, summaries, and chapters from videos in seconds.
Tabby: A Self-Hosted Coding Assistant An open-source code completion server that runs on your own hardware, with editor extensions for VS Code, JetBrains, and Vim, and no code leaving your network.
vLLM: High-Throughput Inference for Serving Many Users A GPU inference server built for throughput rather than convenience, using PagedAttention to serve many concurrent requests efficiently. The right tool when one model must serve a team.
Whishper: Local Audio Transcription and Subtitles With Whisper A self-hosted web app that transcribes audio and video with faster-whisper, exports text and subtitle formats, includes a subtitle editor, and translates through LibreTranslate. AGPL-3.0; a v4 rewrite is in progress.
whisper.cpp: Local Speech Transcription Without a Cloud A C++ port of OpenAI Whisper that transcribes audio on CPU or GPU with no Python stack, suitable for meeting recordings, podcasts, and subtitle generation on your own hardware.
Browse other categories
Notes & Wikis (47) Media Servers (56) Reading & RSS (51) Music (32) Communication (54) Downloads (28) Networking & VPN (38) Monitoring (34) Productivity (45) Photos (21) Containers (36) File Sync (31) CMS & Websites (23) Recipes & Health (20) Home Automation (17) Development (30) Passwords (11) Auth & SSO (14) Analytics (12) Databases (16) Ad Blocking (10) Dashboards (14) Backup (10) Finance (16) Automation (8) Security (19) Games (9)