Local & Self-Hosted AI Tools

Hugging Face Datasets is an open source Python library for preparing data for AI training and evaluation on your own machine. It's for developers and researchers working with local files or datasets from the Hugging Face Hub. The library runs locally; downloading, streaming or sharing data through the Hub uses Hugging Face's hosted service.

CompreFace is a self-hosted face recognition service for developers who want to add facial identification to an application without building or training their own machine learning system. It runs as a Docker-based server on your hardware or in a cloud deployment you manage. It's free and open source under the Apache 2.0 license.

SimpleTuner is an open-source toolkit for fine-tuning image, video and audio generation models on your own hardware or GPU servers. It's for creators and researchers adapting models to their datasets, and teams sharing training infrastructure. A web dashboard manages training jobs.

ScrapeGraphAI is an AI web scraping tool for developers who want to describe the data they need in plain language. Its open-source Python library runs on your own infrastructure under the MIT license. A separate managed API runs in ScrapeGraphAI's cloud.

Zerox is an MIT-licensed OCR library for developers preparing documents for AI applications. Its Node.js and Python packages run on your own machine or server, while cloud vision models read the document pages and produce Markdown. Document conversion happens locally, but page images go to the selected model provider, so this workflow needs internet access and provider credentials.

ChatWise is a desktop chat app for connecting different model providers through one interface. It stores data locally; model processing follows the provider you choose. Its official documentation includes Ollama for models running on your own machine, alongside cloud providers connected with your API keys.

MetaMCP is a self-hosted gateway for developers and teams who want to give AI clients access to several MCP servers through one endpoint. It runs on your own machine or server with Docker and is open source under the MIT license. You choose which tools clients see.

Brave Leo is an AI assistant built into the Brave browser, with Bring Your Own Model support for people who want to use their own local or remote models while browsing. It can work with third-party APIs as well as Brave's hosted model choices. The browser runs on macOS, Windows, Linux, Android, and iOS.

XTuner is an open-source LLM training engine for researchers and teams training large mixture-of-experts (MoE) models on their own hardware. It supports GPU and Ascend NPU training, with an emphasis on memory use and distributed training efficiency at scales reaching a trillion parameters.

MediaPipe is an open-source toolkit for developers adding on-device AI to applications on Android, iOS, the web, desktop and edge devices. It pairs pretrained models with APIs for specific tasks, so developers can use existing solutions or customize them for their applications. The project uses the Apache 2.0 license.

Oumi builds specialized AI models for teams that want control over their training data, model weights, and deployment. Its Apache 2.0 open-source stack runs on laptops, clusters, and your own servers, while its hosted service automates model development from a plain-English task description. You own the resulting weights, data, and training recipes.

EasyOCR is a Python OCR library for developers who want to extract text from images on their own hardware. It reads text in photographs and dense documents, so it can serve both scene-text recognition and document processing. It's open source under Apache 2.0.

Curator is a Python library for developers preparing LLM training datasets or extracting structured records from existing data. It supports local inference through Ollama and vLLM alongside cloud model APIs, so the same data pipeline can use models on your hardware or a hosted provider. It's open source under Apache 2.0.

OpenLLM is a self-hosted LLM server for developers who want to connect their applications to models running on their own hardware or servers. Its OpenAI-compatible API works with clients built for that interface, including the OpenAI Python client and LlamaIndex. The project is open source under the Apache License 2.0.

VideoLingo is a self-hosted video translation app for creators and educators who need bilingual subtitles or dubbed versions of their videos. It brings transcription, translation and subtitle timing into one browser interface, with dubbing as an optional output. The project is open source under Apache 2.0; a separate hosted service offers subtitle translation and dubbing.

Optimum is a collection of Python packages for developers who want to train or run Hugging Face models more efficiently on specific hardware. It extends Transformers, Diffusers, TIMM and Sentence Transformers, with integrations for local machines, mobile and edge devices, and cloud accelerators. It's open source under Apache 2.0.

RVC WebUI is a local AI voice conversion tool for people who want to train a custom voice, change the voice in a recording, or use a live voice changer. It runs on Windows and Linux, including Ubuntu servers, with a browser interface for training and conversion and a separate interface for live use. It's free and open source under the MIT license.

Harbor is a CLI and companion app for people experimenting with AI on their own hardware. It manages a local LLM development environment, connecting model backends to chat interfaces and supporting services so you don't have to configure each connection yourself. It's open source under Apache 2.0.

Detectron2 is an open-source Python library for developers and researchers building computer vision applications. It provides algorithms for locating objects in images and segmenting image regions, with support for training models and building research projects on top of the library. Facebook AI Research developed it as the successor to Detectron and maskrcnn-benchmark.

AllTalk TTS generates speech on your own computer. The project recommends v2 for most users; the saved documentation below describes v1, built on Coqui TTS and XTTSv2 models. It's for people adding voices to AI conversations or producing spoken audio from longer texts. It runs as a standalone application or alongside Text-generation-webui, with support for Windows, Linux and macOS.

ModelScope combines a hosted model and dataset hub with a Python library you can run locally. It's for developers and researchers who want to use AI models in their own applications, fine-tune them on their own data, or compare their performance. The library is open source under Apache 2.0.

SmolChat is an Android app for people who want to chat with language models running on their own phone. It uses llama.cpp to run GGUF models on-device, including small language models. Inference stays on your device.

WhisperWriter turns microphone speech into text and types it into the window you're working in. It's for people who want voice input in their existing desktop apps, with a choice between transcription on their own computer and an external service. The Python app runs on Windows, macOS and Linux and uses the GPL-3.0 open-source license.

llama.rn brings llama.cpp into React Native apps so developers can run local LLM inference on iOS and Android. It's an MIT-licensed library for building AI features into a mobile app, with model processing on the device. It uses GGUF models and requires React Native's New Architecture.

LLM Vision is a free, open-source Home Assistant integration for people who want their smart home to interpret what cameras see. It uses multimodal LLMs to describe images, video files, live feeds and Frigate events, then uses those results in notifications and automations.

OpenLLMetry adds LLM tracing to the OpenTelemetry monitoring stack a team already uses. It's for developers who need to follow model calls alongside database activity and API requests in their AI applications. The extensions run within your application and send standard OpenTelemetry data to your chosen monitoring destination.

Forge is an open-source coding assistant that runs in your terminal and works with models from multiple providers. It's for developers who want an AI agent to edit code and run commands in their own development environment, with a choice of Claude, GPT, OpenAI's O Series, Grok, Deepseek or Gemini.

Claude Code Router is an open-source local model gateway for developers who use coding agents and want to manage their model providers in one place. It runs on macOS, Windows and Linux, with Docker and a CLI with a browser interface also available. The project uses the MIT license.

Scriberr is a free, open source transcription app for people who want to keep meeting recordings and voice notes on their own hardware. It turns audio and video into text locally, with offline transcription once the models are downloaded. The MIT license allows you to use and modify it.

Ray Serve is a self-hosted Python library for developers building inference APIs that combine models with application logic. It runs on a laptop, on-premise servers, Kubernetes, or cloud infrastructure you choose. It's open source under Apache 2.0.

nanochat is an MIT-licensed toolkit for training your own LLM and chatting with it on hardware you control. It's aimed at researchers and developers who want to study or modify the full training pipeline, with a small Python codebase built on PyTorch.

Joplin Jarvis is an AI assistant for people who keep their writing, research, or personal knowledge in Joplin on desktop and mobile. It connects conversations to your existing notes and supports local LLMs through Ollama alongside cloud services such as GPT, Claude, Gemini, and Hugging Face.

Witsy is an AGPL-3.0 desktop AI assistant for macOS, Windows and Linux that connects MCP tools to local and cloud models. It's for people who want document chat, writing help and voice features in one app, with a choice of where their models run.

Docker MCP Gateway gives developers one local connection point for the tools their AI applications use. It runs MCP servers in isolated Docker containers and shares their configuration across clients such as Claude Code, Cursor and Zed. This reduces repeated setup when several coding assistants need access to the same databases, APIs or development tools.

Wyoming Piper connects Piper's local text-to-speech engine to Home Assistant and other clients that use the Wyoming protocol. It's for people building a voice assistant on their own hardware who need speech generation as a self-hosted service. The project is open source under the MIT license.

Augmentoolkit turns your documents into training data for a custom LLM that learns a particular subject. It's for researchers, developers and hobbyists who want models trained on their own material, such as research papers or fictional lore. The Python toolkit is open source under the MIT license and runs on macOS and Linux, with WSL recommended for Windows.

NeMo Curator is an open source Python toolkit for ML engineers and data teams preparing AI training datasets on their own hardware. It handles text, images, video and audio, with reusable pipelines that can run on a laptop or scale across a multi-node Ray cluster. NVIDIA uses it to prepare data for Nemotron models.

Magenta RealTime 2 is a local AI music model and synthesis engine for musicians and developers who want to play or build AI musical instruments on a laptop. It generates streaming audio in real time, with open weights and code under the Apache 2.0 license.

LangBot is a self-hosted AI agent platform for teams that want bots in the messaging apps their customers, coworkers or communities already use. It connects Slack, Discord, Telegram, WeChat and other chat services to models and AI workflows, with a browser dashboard for managing bots across platforms.

Chat2DB Community is a database client and AI SQL workspace for developers, database administrators and analysts. It runs on Windows, macOS and Linux, with Docker and browser access also available. Its AI assistant connects to a model you configure to generate, explain and optimize SQL. Where AI requests are processed depends on that model connection.

Immersive Translate is an AI translation extension and mobile app that keeps original text alongside its translation. It's aimed at students, researchers and people who read foreign-language material for work. The bilingual page layout lets readers compare passages without replacing the source text.

Enconvo is a native AI assistant and agent for Mac that can use your screen and selected text as context, then work inside your apps. It's for people who want help with writing, research and everyday tasks alongside the app they're using. A sidebar keeps the agent beside the current app, while text selection tools give quick access to editing and translation.

ClearML is an MLOps suite for recording experiments, managing datasets and running ML workloads. Its Apache 2.0 Python SDK connects to a ClearML Server, available as a hosted service or open-source software you deploy yourself. ClearML Agent handles job orchestration and reproducibility.

ChatDev is a self-hosted platform for building teams of AI agents through a visual workflow editor. It's for people who want agents to collaborate on research, data analysis or software projects without writing the orchestration code themselves. You define each agent's role and how information passes between them.

InsightFace is a face analysis toolkit for developers and teams building identity verification, access control, or face editing software. The code uses the MIT license. Its Python tools and self-hosted recognition server run inference on your own hardware. It also offers commercial models and API access for face swapping and deepfake detection.

Logseq is an AGPL-3.0 knowledge base with an outline editor, linked references and block references. It combines note-taking with task management, PDF annotations and flashcards. Search and queries can gather related information into tables.

TTS WebUI brings local text-to-speech, music generation and audio processing into one browser interface. It's for people creating spoken audio or music, and for developers who want to add speech to a self-hosted chat app. The interface combines Gradio and React, with extensions that let you choose which audio models to use.

HomeGallery is a self-hosted web gallery for people who want to browse their personal photos and videos while keeping their existing files and folders. It brings multiple media directories into one gallery, with a mobile-friendly browser interface and PWA support. It's open source under MIT.