Self-Hosted AI Tools You Can Run in Docker

DocsGPT is an MIT-licensed, open-source platform for teams that want AI search, assistants and agents over their own documents. It can run on your servers with local models, including fully air-gapped deployments where documents and questions stay inside your network. Answers include the source title and page number so readers can check the evidence.

PDFMathTranslate translates scientific PDFs while keeping their page layout, formulas, charts, contents pages and annotations. It's for researchers, students and others who need to read papers in another language without losing the relationship between the text and its figures. It produces both translated PDFs and bilingual documents for comparison with the original.

pgvectorscale adds an index for large embedding datasets to PostgreSQL databases that use pgvector. It's for application developers and database administrators who want to keep AI similarity search in their existing database, with more control over search speed and storage use.

Text Embeddings Inference is a self-hosted server for developers who need text embeddings for search and retrieval applications. It serves models through a REST API on your own hardware and can run offline once model weights are downloaded. The Rust project is open source under Apache 2.0.

PrivateGPT is a self-hosted API layer for developers building AI applications around local models. It adds document retrieval, database access and agent tools to an existing model server. Local workflows can work offline and keep data within your environment; web search and connections to online providers need internet access.

Roboflow Inference is a self-hosted computer vision server for teams building camera and image analysis systems. It runs on your own computer, server, or edge device and combines model predictions with workflows for tracking, counting, measuring, and responding to events. Roboflow also offers hosted servers and a Serverless Cloud API, where processing runs on its infrastructure.

ebook2audiobook turns non-DRM ebooks into narrated audio with chapters and metadata, for readers who want audio editions of their own books. It runs locally on Windows, macOS and Linux, with Docker support and a browser interface built with Gradio. It's open source under Apache 2.0.

Lemonade is an open source local AI server for people who want to use models on their own hardware or connect them to apps and agents. It handles chat, coding, image generation, speech, transcription, and embeddings. A built-in interface lets you use those capabilities directly, while its server makes them available to other software.

Lingarr is a self-hosted subtitle translator for people who maintain a media library and want subtitles in another language. It automates translation of subtitle files using a service you choose, with support for both local AI and hosted translation providers.

Windmill turns ordinary scripts into APIs, background jobs and internal apps that teams can share through a browser. It's for developers building internal software, data pipelines or AI agents who want to keep their code and infrastructure under their own control. You can self-host it with Docker or Kubernetes, or use Windmill Cloud, where Windmill hosts the platform.

Presidio is a self-hosted Python framework for developers and organizations that need to detect and remove personally identifiable information (PII) from text, images and structured data. It can identify names, credit card numbers, social security numbers and other sensitive details, then redact, mask or anonymize them. It's open source under the MIT license.

Local Deep Research is a self-hosted AI research assistant for people who need cited answers drawn from academic papers, the web and their own documents. It can produce a quick summary or pursue a complex question through repeated searches, then assemble a structured report. It's open source under MIT.

txtai is a Python framework for developers building search applications, chat with their data, and AI agents on their own hardware or servers. Its embeddings database combines sparse and dense vector search with graphs and relational data, so the same system can find related content and supply context to language models. It's open source under Apache 2.0.

Chatwoot is a self-hosted customer support platform for teams considering an alternative to Intercom or Zendesk. It combines a shared inbox, an AI agent called Captain, and a help center. You can host the platform on your own server to control your customer data, or use Chatwoot's hosted cloud service.

Label Studio is a self-hosted platform for teams preparing training data or evaluating AI outputs through human review. It handles text, images, audio, video and time series in the same application, including tasks that combine several data types. The open source edition uses the Apache 2.0 license and runs locally or on your own server, with Docker deployment and browser access. A separate hosted cloud edition runs on the provider's infrastructure.

Tiledesk is a self-hosted platform for building AI agents and connecting them to human support teams. It's aimed at businesses automating customer conversations, internal information searches and workflows through a visual builder. You can run it on your own server with Docker or Kubernetes, or use its hosted cloud service.

TensorRT-LLM is a library for developers running LLMs on their own NVIDIA GPUs or self-hosted servers. It focuses on inference performance, with support for a single GPU, multiple GPUs, or deployments spread across several machines. Its PyTorch architecture lets teams adapt models and extend the runtime in Python.

Jina Reader turns web pages and documents into text that LLMs can use, with Markdown or JSON output. It's for developers building AI agents, search tools and systems that answer questions using retrieved documents. You can self-host the Apache 2.0 service code in Docker or use Jina's hosted API.

Speaches is a self-hosted speech server for developers who want transcription, translation and speech generation on their own hardware. Its OpenAI-compatible API lets applications use local speech models through tools and SDKs built for OpenAI's API. The project is open source under the MIT license.

Playwright MCP lets AI agents control a browser by reading structured page information rather than interpreting screenshots. It's for developers building browser automation, exploratory tests or agent workflows that need to keep a browser session open across repeated actions. The server runs locally on macOS, Windows and Linux, or as a self-hosted service.

Xinference serves language, speech and multimodal models through a shared API on your own computer or servers. It's an open source platform under Apache 2.0 for developers and researchers who want to build applications around models they host. You can also deploy it on cloud infrastructure.

llama-swap is a self-hosted proxy for people running several AI models on their own hardware. It starts the model server a request needs and swaps out another when necessary, so you don't have to keep every model loaded or manage separate API connections in your apps.

KTransformers is an open-source framework for running and fine-tuning large language models on your own hardware. It focuses on mixture-of-experts (MoE) models, distributing work between CPU memory and GPU resources to reduce the GPU memory needed. It's aimed at researchers and developers who want to serve or adapt models such as DeepSeek-V3 and DeepSeek-R1.

PandasAI is a Python library for people who want to ask questions about their data in plain language. It works with SQL databases, CSV and parquet data, and can answer questions across multiple pandas DataFrames. Developers can use it in their own applications; analysts can use conversational queries to reduce the code they write for individual questions.

Megatron-LM is a Python framework for research teams training large language models on NVIDIA GPU infrastructure. It pairs ready-made training scripts with Megatron Core, a library developers can use to build their own training systems. Its focus is distributed training, with benchmarks on H100 clusters spanning thousands of GPUs.

GPT4All is a local AI chatbot for people who want to run language models on their own desktop or laptop and keep conversations on their machine. Its LocalDocs feature lets you ask questions about your own documents without sending them to a cloud service. It suits developers, teams and individuals who want control over their models and data.

subgen generates subtitles on your own hardware for personal media libraries, including films and shows that don't have usable subtitles available. It's an open source, MIT-licensed Python service that runs in Docker or as a standalone application. Speech recognition runs locally using Whisper models through faster-whisper and stable-ts, with support for CPU processing and NVIDIA GPUs through CUDA.

FastGPT is a self-hosted AI agent builder for teams that want assistants to answer questions using company documents and carry out business workflows. Its visual editor connects model calls, knowledge retrieval and tools into applications for customer support, internal knowledge search and document review. You can run the platform on your own server through Docker or use the vendor's hosted service.

Weaviate is a self-hosted vector database for developers building search applications, RAG systems, recommendation engines, and chatbots. It stores data objects alongside their vector embeddings, so applications can search by meaning and filter results using structured data. You can run the database locally with Docker, deploy it on Kubernetes, or use the hosted Weaviate Cloud service.

jetson-stats monitors NVIDIA Jetson hardware and gives you control over its power and cooling settings. It runs locally on the board, with a terminal interface called jtop for people developing or running workloads on Jetson devices, including local AI applications.

Cognee gives AI agents persistent memory across sessions, connecting documents, code, and conversations in a searchable knowledge graph. It's for developers who want agents to retain project context and teams whose knowledge sits across tickets, discussions, and repositories. The Python package is open source under Apache 2.0.

Repomix turns a code repository into a single file that an AI assistant can read. It’s for developers who need to give Claude, ChatGPT, Gemini, or another model enough project context for code review or analysis. You can use its command line on your own machine, pack a repository through its website, or run it as an MCP server, including through Docker. It is open source under the MIT license.

big-AGI is a browser-based AI workspace for researchers, developers and people who want to compare model answers before relying on them. Its Beam feature sends the same prompt to several models in parallel, without letting them see each other's replies. You can examine disagreements, then use Merge to combine the responses into a single answer with a preset or custom prompt.

olmOCR is an open-source OCR toolkit for turning PDFs and image documents into text for LLM datasets and training. It suits researchers and developers who need readable document content, including pages where columns, figures, or mathematical notation make text extraction difficult. You can run it on your own GPU, including through Docker, or use a remote inference server.

Chatterbox TTS Server runs Resemble AI's speech models on your own computer or server, with a browser interface and an OpenAI-compatible API. It's for people producing narration and audiobooks, or developers adding speech to voice agents and other apps. The project is open source under the MIT license.

Vexa is a meeting bot and transcription API for developers building meeting features and teams feeding calls into AI agents. Bots join Google Meet, Microsoft Teams and Zoom, then send live transcripts with speaker labels to your application or agent. You can host the full platform on your own infrastructure or use Vexa's cloud service.