Self-Hosted AI Tools You Can Run in Docker

Pi is a terminal-based coding assistant for developers who want to shape the agent around their own workflow. Its core stays small, while extensions can change its tools, commands and terminal interface. It's open source under the MIT license.

Photoview is a self-hosted photo gallery for photographers and households who keep their pictures on a personal server or NAS. It turns existing folders into browser-based albums and automatically scans for added photos and videos. Your folder structure determines how the library appears, so you can keep organizing files through Samba, FTP or Nextcloud. Your media stays on your server.

Bisheng is an open source, self-hosted platform for teams building AI applications around business documents and processes. Its visual workflow editor combines automated tasks with human feedback, including intervention during multi-turn conversations. It's suited to document review, support ticket assistance and report generation that need more control than a single chatbot exchange.

Pezzo is an open-source platform for developers and teams managing prompts and monitoring LLM applications. You can run the full stack locally with Docker Compose, keeping the prompt management and monitoring platform on infrastructure you control. Its source code uses the Apache 2.0 license.

Vigil is a self-hosted security scanner for developers and researchers who want to check LLM inputs and responses for prompt injection, jailbreak attempts, and other suspicious content. It combines several detection methods and includes attack signatures and datasets, so teams can assess known threats without building every detector themselves. It is experimental alpha software for research and is open source under Apache 2.0.

GoModel is a self-hosted AI gateway for developers and platform teams that want one API for local models and cloud providers. It accepts OpenAI- and Anthropic-compatible requests, so applications can keep their existing SDKs while the gateway handles provider selection and usage controls.

Agent Router is an open source AI gateway for teams whose agents use both model APIs and MCP tools. It runs on a laptop, a dedicated gateway, or Kubernetes, and gives applications one OpenAI-compatible entry point for cloud providers and self-hosted inference. The project uses the Apache 2.0 license.

BricksLLM is a self-hosted AI gateway for teams that need to control access and spending across LLM applications. It sits between applications and model providers, applying cost and rate limits to individual API keys. The gateway is open source under the MIT license and runs locally or on your server through Docker, with PostgreSQL and Redis.

One API is a self-hosted LLM API gateway for developers and teams that want to share model access across apps or users. It puts cloud providers and Ollama behind an OpenAI-compatible API, so clients can use one endpoint across different backends. It's open source under MIT and runs on your own server as a single executable or in Docker.

Ollama Helm Chart packages Ollama for teams that want to run a local LLM service on their own Kubernetes cluster. It's a community-maintained, open source chart under the MIT license, aimed at developers and infrastructure teams managing AI alongside other cluster services.

Wyoming Satellite connects a microphone and audio playback device to Home Assistant through the Wyoming protocol. It's for people building a self-hosted voice assistant with a separate device for speaking and listening. The project is archived and no longer maintained; its replacement is Linux Voice Assistant, which uses the ESPHome protocol.

Spleeter is Deezer's music source separation library for developers and audio researchers who want to split recordings into separate vocal and instrumental tracks on their own hardware. It includes pretrained models, so you can separate audio without first training a model. The library is open source under the MIT license.

Demucs separates a finished song into vocals, drums, bass and the remaining accompaniment on your own computer. It's for musicians who need individual stems or a vocal-free backing track, and developers building audio tools. The project is archived and no longer maintained. Its Python code is open source under the MIT license.

Vocode is an open source Python library for developers building voice AI agents, with a self-hosted telephony server and support for live conversations through a computer's microphone and speakers. It connects speech recognition, an LLM, and speech synthesis in one library. The code uses the MIT license.

Bolna is a voice AI agent platform for businesses handling customer support, lead qualification, reminders, and recruitment calls. Its focus is Indian languages and accents, including Hindi, Hinglish, Tamil, and Telugu, alongside English. Developers can self-host its MIT-licensed Python orchestration core, while business teams can use a hosted dashboard to build agents without code.

Supergateway connects MCP servers and AI clients that use different connection types. It's for developers who want to expose a local tool server over a network or connect a desktop client to a remote server. The gateway runs on your own machine or server through Node.js or Docker, and its code is open source under the MIT license.

mcp-proxy is a self-hosted tool for connecting AI clients and MCP servers that use different connection types. It's for developers who need a stdio client, such as Claude Desktop, to reach an SSE or Streamable HTTP server, or who want remote clients to access a local stdio server. The proxy runs on your own machine or server.

MindsDB Query Engine is a self-hosted server for developers building AI agents that need access to business data and documents. It queries connected sources through one SQL dialect and adds semantic search for unstructured content. You can run it locally or on your own server with Docker. Its core uses the Elastic License 2.0, with separate licenses in some directories.

DeepStack is a self-hosted computer vision API for developers adding image analysis to camera systems, home automation or other applications. It runs prebuilt and custom models on your own hardware and works fully offline. Image processing stays on the device or server where you host it, with no cloud service required.

CodeProject.AI Server gives developers a shared API for AI tasks that run on their own hardware. It's a self-hosted service for adding image analysis, text processing and generation to applications. Processing stays on the machine running the server, without cloud calls or sending data outside your device or network.

Double Take connects Frigate camera images to facial recognition services through a shared web interface and API. It's for people running camera systems and Home Assistant who want to identify familiar faces and use the results in home automations. The app runs on your own server in Docker and is open source under the MIT license.

Fooocus is a free, open-source AI image generator for people who want to create images on their own computer without spending much time tuning settings. It uses Stable Diffusion XL and automatically expands prompts with a local GPT-2 engine. Generation works offline once the required models are downloaded, so prompts and images can stay on your machine.

h2oGPT is a self-hosted ChatGPT alternative for people who want to chat with local models and ask questions about their own documents. The project is archived and no longer maintained. It's open source under Apache 2.0, with support for Linux, macOS, Windows and Docker.

QAnything is a self-hosted knowledge base for people and teams who want to ask questions about their own documents, including collections that mix Chinese and English. It can answer in either language regardless of the document's language, and runs locally through Docker on Windows, macOS and Linux.

Qwen3-Embedding is a family of text embedding models for developers building search and document analysis on their own hardware or servers. It turns text into numerical representations that applications can compare by meaning. Its multilingual support covers languages including English, Chinese, Arabic and Ukrainian, as well as programming languages.

Discord Ollama Bot connects locally hosted language models to Discord, so a community can use an AI assistant inside its existing chat server. It's for server owners who want to choose and host the models themselves while keeping Discord as the interface. Model inference runs on your hardware, but conversations still pass through Discord, so this isn't a fully offline chat app.

FluxGym is a local web interface for training FLUX LoRAs on your own images, with support for GPUs with 12GB, 16GB or 20GB of VRAM. It's for people who want to customize an image model through a browser while retaining access to detailed training controls. It runs on Windows and Linux, with Docker support, and is open source under the MIT license.

OpenedAI Speech is a self-hosted text-to-speech server for developers who want local speech generation in apps built around OpenAI's speech API. The project is archived and no longer maintained. It's open source under AGPL-3.0, and it generates audio on your own hardware without an OpenAI API key.

Verba is a self-hosted document chatbot for people who want to ask questions across their files and knowledge bases. The project is archived and no longer maintained. It uses Weaviate to find relevant passages and gives those passages to a language model to generate answers.

Zep Community Edition v1.0.2 is a deprecated, unsupported self-hosted memory service for developers building AI agents and conversational assistants. This legacy edition uses the Apache 2.0 license. It turns chat history into a knowledge graph that records how facts change over time, so an assistant can distinguish a user's current preferences from earlier ones.

RAGapp is a self-hosted app for teams that want an AI assistant using retrieval-augmented generation (RAG) on their own infrastructure. It pairs a browser chat interface with an admin interface for configuring the assistant, taking an approach similar to OpenAI's custom GPTs. It's open source under the Apache 2.0 license.

Morphic is a self-hosted AI search engine for people who want answers backed by web sources and control over the search interface they use. It combines web searches and URL reading with AI-generated responses, so you can examine the sources behind an answer. It's open source under Apache 2.0, and you can run your own instance with Docker or use the hosted website.

Farfalle is a self-hosted AI search engine for people who want a Perplexity-style search app with a choice of local or cloud models. It combines web search with model-generated answers and includes an agent that plans and carries out searches. The code is open source under Apache 2.0.

Flowise is a visual builder for AI agents and chatbots that can run locally or on your own server, including through Docker. It's for developers and teams building LLM applications with connected workflow blocks. The project is archived and no longer maintained.

OpenUI is a self-hosted AI UI builder for developers prototyping web interfaces with models they choose. It turns plain-language descriptions into rendered interfaces, with a live preview and follow-up requests for changes. You can run the app locally through Docker or Python and use it in your browser.

GPT Pilot is a self-hosted AI coding assistant for developers who want an agent to build applications under their supervision. The project is no longer maintained. It uses the FSL-1.1-MIT source-available license, with restrictions on competing uses. It runs locally as a Python CLI and is the core technology behind the Pythagora VS Code extension.