Self-Hosted AI Tools You Can Run in Docker

DB-GPT is a self-hosted AI data assistant for teams analyzing business data and developers building data applications. It turns plain-language requests into SQL queries and Python analysis, then produces charts, dashboards, or HTML reports. You can run it on macOS or Linux, with Docker deployment also supported.

LibrePhotos is a self-hosted photo manager for people who want to organize a photo library on their own server, with AI tools for finding images and grouping faces. It scans files already on your storage and supports RAW photos as well as videos. The project is open source under the MIT license.

ZoneMinder is a self-hosted video surveillance system for people who want to manage security cameras on their own Linux machine. It brings video capture, analysis, recording and monitoring into one system, with support for IP, USB and analog cameras. It's free and open source under the GNU General Public License v2.0 (GPL-2.0).

Codestral and Devstral are Mistral coding models with downloadable weights for local or self-hosted development tools. Codestral focuses on code generation and fill-in-the-middle completion, where the model fills a gap between existing code. Devstral is designed for software engineering agents that explore a repository, use tools and edit multiple files.

Mistral Small and Large are downloadable language models for developers building chat, reasoning and tool-using applications on their own infrastructure. Capabilities and hardware requirements depend on the release. Mistral Small 3.1 adds image understanding to text generation, while Mistral Large 2 is a larger text model.

Plano, formerly Arch Gateway, is a self-hosted AI gateway for developers building applications with multiple agents or model providers. It puts routing, guardrails and request tracing in a separate service, so each agent doesn't need its own implementation of that infrastructure. It's open source under Apache 2.0.

SwarmUI is a self-hosted AI image generation interface that combines a straightforward generation screen with direct access to ComfyUI's node-based workflows. It's for people who want to run creative models on their own hardware, with room to build more detailed workflows as their needs grow.

Unstructured is a local document processing library for developers building LLM applications and document ingestion pipelines. It turns PDFs, Word documents, HTML, emails and images into document elements that applications can use. The Python library is open source under Apache 2.0 and runs on your own hardware, including through Docker images for x86_64 and Apple Silicon.

Portkey Gateway is a self-hosted AI gateway for developers whose apps need to use local models and cloud providers through one OpenAI-compatible API. It routes requests to Ollama, OpenAI, Anthropic, Google Gemini and other backends, with controls for handling failures and checking model inputs and outputs.

Morphik Core is a self-hosted multimodal retrieval engine for developers building AI applications around visually rich documents. It searches diagrams, schematics, charts, and datasheets alongside text, so applications can retrieve information that text extraction alone can miss. You can run it on your own server, including through Docker, or use Morphik's hosted service.

Marqo Open Source is a self-hosted search engine for developers building semantic document search, image search, or retrieval for AI applications. It handles embedding generation alongside storage and retrieval, so applications can submit documents without maintaining a separate embedding service. The open-source project is deprecated and no longer receives updates.

Plandex is an open source, terminal-based AI coding agent for developers working on changes that span many files. Its review sandbox holds generated edits apart from your project files so you can inspect the accumulated changes before applying them. You can run its server locally through Docker or host it on your own server. The code uses the MIT license.

NextChat is a self-hosted AI chat interface for people who want one place to use their own LLM server and cloud models. The web and desktop project is open source under the MIT license. You can host it with Docker or on Vercel, and desktop clients run on macOS, Windows and Linux.

R2R is a self-hosted AI retrieval system for developers building applications that answer questions using their own documents. It combines search, retrieval-augmented generation (RAG) and a reasoning agent behind a REST API. The project is open source under the MIT license and runs as a Python service or in Docker.

CosyVoice is a local text-to-speech system for developers and researchers who want to generate speech in a reference speaker's voice, including in another language. Its zero-shot voice cloning doesn't require training a separate model for each speaker. You can run it on your own hardware or deploy it as a self-hosted service.

Yi is a family of open-weight language models from 01.AI for developers, researchers, and businesses that want to run English and Chinese models on their own hardware. It includes models for conversation and base models for fine-tuning, with license terms that depend on the release. Yi-1.5 code and weights use Apache 2.0; the original Yi releases have separate community terms.

JoyCaption is an open-weight image captioning model for people preparing datasets to train or fine-tune diffusion models. It runs on your own GPU and covers both SFW and NSFW images, including photography, anime, digital art and furry artwork. Automated captions reduce the need to write descriptions by hand or find images that already have usable text.

Grounding DINO finds objects in images using category names or descriptive phrases you supply. It's a local AI model for developers and computer vision researchers who need detection beyond a fixed set of labels, including people building dataset annotation tools.

Tortoise TTS is a local text-to-speech system for developers and creators who want speech with varied voices and natural pacing. It uses reference audio clips to guide a custom voice, with an emphasis on expressive rhythm and intonation.

Intel IPEX-LLM is a library for developers running or fine-tuning models on Intel hardware. The project is archived and no longer maintained. Intel reports known security issues and no longer accepts patches or provides updates. The code is open source under Apache 2.0.

Text Generation Inference (TGI) is a self-hosted LLM server for developers and teams serving models through an API on their own hardware. The repository is archived; its README describes maintenance mode and recommends other inference engines for new deployments. Its focus is handling concurrent generation requests and making efficient use of GPU memory.

Dia is the original text-to-speech model from Nari Labs that generates a two-speaker conversation from a written script in one pass. It's for researchers and developers who want to generate English dialogue on their own hardware, with control over speaker voices and delivery. The code and model weights are available under Apache 2.0. Dia2 is a separately linked successor.

GLaDOS is a local AI voice assistant modeled on the sarcastic character from Valve's Portal games. It's for people who want a conversational companion on their own hardware, with camera awareness and connections to home automation. The Python project is open source under the MIT license and runs on Linux and Windows. macOS support is experimental.

Hollama is an open-source LLM chat app whose interface runs entirely in your browser. It's for people who want to chat with local AI through Ollama or connect to OpenAI servers, with support for multiple server connections. The interface stores data locally in the browser; the connected server handles model requests, so where inference runs depends on the server you choose.

Wav2Lip is a local AI lip-sync tool that changes a face's mouth movements in an existing video to match supplied speech. It's for researchers and people making academic or personal video projects who want to process their own files. Commercial use is prohibited under the project's stated terms because its models were trained on the LRS2 dataset.

docTR is an open-source Python OCR library for developers building document processing tools and researchers comparing text recognition models. It reads PDFs and images on your own hardware, locating words and recognizing their text. The library uses PyTorch and carries the Apache 2.0 license.

Laminar is an open-source platform for developers who need to see why an AI agent failed and check whether a fix worked. You can self-host it with Docker or on Kubernetes, including AWS and GCP, or use its managed cloud service. It uses the Apache 2.0 license.

Nextcloud Recognize automatically categorizes media on your self-hosted Nextcloud server. It's for people who want to organize photo, video and music collections without sending sensitive data to a cloud recognition service. Image processing runs on your Nextcloud machine.

HuggingChat UI is the open-source chat application behind Hugging Face's hosted HuggingChat. You can run it on your own computer or server and connect it to a local LLM backend or a cloud provider. It's for people and teams who want a browser-based ChatGPT alternative with control over the chat service and where its data lives. The code uses the Apache 2.0 license.

Meme Search is a free, self-hosted web app for people who want to find memes in their own collection by image content or text. It runs locally through Docker and uses AI descriptions to make images searchable, even when their filenames aren't useful. The code uses the Apache 2.0 license.

F5-TTS is a local text-to-speech system that uses a reference recording to generate new speech in that voice without training a separate model for each speaker. It's for developers, speech researchers, and creators who want to generate voices on their own hardware. Its Python code uses MIT, while pretrained models use the noncommercial CC-BY-NC license.

xberg, formerly Kreuzberg, is a local document extraction engine for developers building AI search, document processing, and retrieval-augmented generation applications. It reads PDFs, Office files, scanned images, email, and nested archives, extracting text, tables, images, and metadata through one shared engine. It's open source under MIT.

Unmute adds spoken conversation to text LLMs using Kyutai's speech recognition and speech synthesis models. It's for developers who want a self-hosted voice interface while keeping their choice of language model. The project uses the MIT license, and a hosted browser demo is available at Unmute.sh.

SenseVoice is a local speech recognition model that adds language, emotion and sound-event tags to transcriptions. It's for developers building voice applications or analyzing recordings on their own hardware, particularly those working with Mandarin and Cantonese. The project is open source under the MIT license.

MTEB is an Apache 2.0 Python toolkit for evaluating embedding models and retrieval systems. It runs evaluations through Python or a command-line interface and publishes an interactive leaderboard.

MeloTTS is a Python text-to-speech library for developers who want to generate speech locally, including on machines without a dedicated GPU. It supports real-time inference on a CPU. Its language and accent choices make it relevant for applications that need spoken output across different audiences.