Self-Hosted AI Tools You Can Run in Docker

MirrorMate puts a voice assistant in a physical mirror for people who want to ask questions, check daily information or chat without reaching for a phone. It remembers details from conversations to personalize later responses.

Sandbox Agent lets developers control coding agents from their own applications through a shared API. It's for teams building agent-powered software that needs remote sessions and isolated code execution without a separate integration for each agent.

Civitai is a platform for creators to share AI image models, browse other people's work and exchange feedback. You can self-host its model-sharing platform, but image generation and training don't work in the local setup.

Chat with GPT is an unofficial ChatGPT client for people who want voice conversations and control over the chat interface. You can self-host the app, but its AI chat and speech recognition depend on OpenAI's cloud services.

DEEIX Chat is a self-hosted AI workspace for individuals and teams that want one place to use multiple model providers. It combines everyday chat with controls for organizations managing shared model access and usage.

Transcription Stream turns recordings into transcripts with speaker labels for people who need to review audio on their own hardware. It works fully offline, including summaries through Ollama and Mistral.

ServiceStack AI Server is a self-hosted gateway for developers and teams whose applications use several AI providers. It runs in a Docker container and gives apps one API integration for local models, cloud LLMs and media processing. Teams can change providers without changing their client integrations.

MLflow helps developers and teams inspect AI applications, compare changes and track model experiments. It brings agent debugging and evaluation into a platform you can run locally or on your own servers.

Folio OCR is a local AI workbench for turning scanned PDFs, book photos and document images into editable text. It's aimed at book digitization and batch transcription where headings, paragraphs and tables need to survive recognition.

Plano is a self-hosted AI gateway for developers building applications with multiple agents. It handles shared routing, orchestration and monitoring outside the agents, so developers don't need to build those functions into each one.

NVIDIA cuML is a Python machine learning library for data scientists whose scikit-learn, UMAP or HDBSCAN workloads take too long on a CPU. It runs on NVIDIA GPUs in Linux or WSL 2, on a workstation or across a cluster. The project is open source under Apache 2.0.

DeepLabCut is an open-source toolbox for researchers who want to track animal movement and behavior on their own computers without attaching physical markers. It estimates the positions of visible features you choose, with support for animals, humans and objects rather than a fixed set of species or body parts.

TensorRT Model Optimizer (ModelOpt) is a Python library for developers who need smaller models and faster inference. It accepts Hugging Face, PyTorch and ONNX models and lets developers combine optimization techniques before deployment.

BankMCP connects an AI assistant to your own European bank accounts so you can ask about spending, balances and incoming payments. It's a self-hosted connector for one user, with read-only access: it can't make payments.

Palace gives AI coding agents persistent memory of project decisions, conventions and fixes. Developers can carry that context between sessions in Cursor, Claude Code, Codex and Claude Desktop.

Translate Books With LLMs translates books, documents and subtitles using a local or cloud model. It's for readers and translators working with long texts who need formatting and terminology to carry through the translation.

llmcord is a self-hosted Discord bot for people who want to share AI conversations with friends or a community. It connects Discord chats to local models or remote providers. Conversation history stays in Discord, even when the model runs on your own hardware.

SiYuan is a knowledge workspace for people who want to connect notes, reference material and individual passages. Its block-based editor lets you link directly to a piece of text rather than an entire document.

RapidOCR is an OCR toolkit for developers who need to extract text from images within their own applications. It uses models derived from PaddleOCR and can run recognition offline on local hardware.

PicoClaw is a self-hosted personal AI assistant that can use local models through Ollama or vLLM. It's aimed at people who want an agent on their own hardware, including small Linux boards and Android phones. Hosted providers are optional, but choosing OpenAI, Anthropic, Google Gemini or DeepSeek sends model requests to those services and requires internet access and API keys.

Coding Tools MCP gives AI chat apps and coding agents access to a repository on your machine. It's for developers who want to use an existing MCP client to inspect code, make edits and check a running project.

EverShelf helps households keep track of food and choose meals that use what's already in the kitchen. It covers the pantry, fridge and freezer, with optional AI assistance.

WhisperLive turns speech into text as audio arrives, using OpenAI's Whisper models. It's for developers and teams who want to run transcription on their own machine or server and connect it to live audio or recorded files.

Octipus is a self-hosted AI workspace for people who want agents to work on code, research, and recurring tasks while keeping the results open to review. A lead agent can use tools itself or assign bounded work to specialist agents. You can inspect the sources, changes, checks, and execution records behind an answer.

Zengram gives AI agents a shared memory across sessions and machines. It's for people using multiple assistants who want a discovery recorded by one agent to be available to the others.

olmOCR converts scanned and image-based documents into text for researchers and developers preparing LLM datasets. It handles pages whose layout makes ordinary text extraction difficult.

GPT4All is a local AI chatbot for people who want language models and document conversations on their own computer. Model inference and LocalDocs processing run on the device without a cloud connection.

Baserow is a self-hosted no-code database and application builder with a spreadsheet interface. Teams can deploy it through Docker or Helm, or use Baserow Cloud. The open-source core is MIT licensed, with additional commercial capabilities.

NextChat is an AI chat interface for people who want to use self-deployed LLMs and cloud models in one application. It connects to LocalAI and RWKV-Runner, and supports OpenAI, Claude, Google Gemini and DeepSeek.

Navigator is a self-hosted AI workspace for individuals and teams who want assistants to carry out tasks through connected tools. It combines chat with custom agents and reusable visual workflows.

Tel-Agent is an AI receptionist for businesses that want phone calls and customer messages handled by one agent on their own server. Recordings and transcripts stay on your machine, but its voice setup uses Deepgram, a cloud LLM and ElevenLabs, requiring internet access and your own API keys.

GPT Researcher is an AI research agent for people who need detailed reports based on web evidence, their own documents, or both. It investigates a question and writes a report with inline citations readers can check.

InstantMesh generates 3D meshes from a single image. It's for creators working with image-based 3D assets and researchers studying 3D reconstruction.

OpenCrust is a self-hosted AI assistant platform for people who want agents to handle tasks through their messaging apps. Named agents can pass work to one another and retain conversation memory between sessions.