Local & Self-Hosted AI Tools

RAGFlow is an Apache 2.0 licensed RAG engine for teams building AI agents that need to answer questions from their own documents. It can run on a self-hosted server through Docker on Windows, macOS or Linux. A separate hosted cloud service is available.

Noema is a private local AI assistant for iPhone, iPad, Mac, and Vision Pro. It's for people who want to chat with models and work with their own files on Apple hardware without depending on a cloud service. Local chats can stay on your device, and file retrieval runs there too.

Open Notebook is a self-hosted alternative to Google's NotebookLM for researchers, students, and professionals who want AI help with their own research materials. It runs locally or on your server through Docker and is open source under the MIT license. You choose which content the AI can access and which provider processes it.

LM Studio is a desktop application for downloading and running language models on macOS, Windows and Linux. You can search for models, manage downloads and chat with them through the app. Downloaded models can run offline, including document chat that uses files on your computer.

FaceFusion is an AI face manipulation tool for photos and videos that processes media on your own machine. It's aimed at content creators, VFX artists, and film studios that want control over their footage and personal data. Local processing keeps that media on your hardware rather than sending it to a cloud service.

Frigate is an open source NVR for IP cameras that detects people, cars, and other objects on your own hardware. Camera feeds stay at home. It's built for people who want a locally controlled security camera system, particularly those using Home Assistant.

llama.cpp runs language models on your own hardware and can serve them from a machine you control. It’s an MIT-licensed, open source inference engine for people building local AI apps, running a private model server, or using a model directly from the command line. It supports vision-language models too.

Chatterbox is an MIT-licensed text-to-speech model family for developers and creators who want to generate speech on their own hardware. You can self-host it on a GPU, including in an air-gapped environment, without an account or API key. Resemble AI also offers separate managed hosting.

Activepieces brings AI agents and workflow automation into one workspace for teams that need to connect their apps and internal data. It runs on your own servers with Docker or Kubernetes, or as a managed cloud service. An isolated deployment can keep platform data on its own infrastructure; connected apps and model providers may still require external access. Its core and app integration pieces are MIT-licensed.

Immich is a self-hosted photo and video library for people who want their pictures on their own server. Its mobile apps for iOS and Android back up photos and videos, while the web interface gives each user a place to browse and manage their collection. The project is open source under the GNU AGPL v3 license.

Gemma is Google DeepMind’s family of open-weight AI models for developers building applications that can run on their own hardware. Its range covers compact models for phones and IoT devices alongside larger Gemma 4 models for reasoning on personal computers and servers. Some applications can work offline, keeping model inference on the device. Google AI Studio and Google Cloud are also available for hosted use.

Serena is a locally run MCP toolkit that gives AI coding agents access to code structure: functions, classes and the references between them. It's for developers who want their agent to find and change specific parts of a codebase without reading whole files or relying on text matching. It requires an LLM client and works with Claude Code, Codex, OpenCode, Cursor and OpenWebUI.

Cua gives AI agents access to computers they can inspect and operate, with tools for desktop automation, local virtual machines, and hosted fleets. It's for developers building agents that work across native apps and browsers, or evaluating how well those agents complete computer tasks. You bring the agent and model.

ComfyUI is a local visual AI workspace for artists and technical teams who want to control how images, video, audio, 3D models and text are made. Its node canvas shows each model and processing step, so users can build and adjust workflows without writing code. It runs on your hardware.

Langfuse is an open source observability and evaluation platform for teams building LLM applications and AI agents. It shows the steps behind a response so developers can investigate failures, slow requests, and cost. Teams can run its MIT-licensed core on their own servers with Docker Compose or Kubernetes, or use Langfuse Cloud as a hosted service.

IndexTTS, currently IndexTTS-2.5, is a local text-to-speech system that can reproduce a speaker's voice using one reference recording. It's for people creating spoken audio and developers building speech generation into their own applications. Voice identity and emotion have separate controls, so an emotional reference can shape the delivery while a different recording supplies the voice.

Context7 brings current library documentation and code examples into an AI coding assistant's context. It's for developers who want answers grounded in the libraries and versions they're actually using, rather than an assistant's older training data. It works with Claude Code, Codex, Cursor, Devin Desktop and Antigravity.

Pydantic AI is a Python SDK for developers building AI agents into their own applications. Its main draw is Pydantic validation across agent tools and results, so an agent can return structured data that application code can check and use. The SDK is MIT licensed.

Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.

Hermes Agent is a self-hosted AI agent from Nous Research for people who want an assistant that remembers past work and develops reusable skills. It creates skills after complex tasks, revises them through use, and searches earlier conversations to recover context across sessions. The project is open source under the MIT license.

AFFiNE is a local-first knowledge workspace for individuals and teams who want documents and visual planning in the same place. It combines a block editor, an edgeless whiteboard and databases, making it an alternative to Notion and Miro for team wikis, project plans and connected notes.

MLX is a machine learning array framework for researchers and developers building models on their own hardware. Its distinctive feature on Apple silicon is shared CPU and GPU memory: both processors can work on the same arrays without copying data between them. It's open source under the MIT license.

LLaMA-Factory is an open-source framework for developers and researchers who want to adapt language and multimodal models on their own hardware. It brings training and inference into one toolkit, with support for LLaMA, Qwen3, Qwen3-VL, DeepSeek, Gemma, Mistral and LLaVA. Its license is Apache 2.0.

Cherry Studio is a free, open source desktop app for people who use several AI models and want their conversations in one place. It runs on Windows, macOS and Linux. Chats, settings and knowledge base files are stored on your device.

InvokeAI is a free, open-source image generator for artists and production teams who want to create and edit images on their own hardware. Its locally hosted web interface brings image generation, canvas editing and workflow tools into one application. With local models, prompts and artwork stay on the machine you control.

n8n lets technical teams build AI agents and business workflows in a visual editor, then add JavaScript or Python where they need more control. Each step shows its inputs and outputs, so teams can inspect how an agent reached a decision and what happened next.

SiYuan is a local-first, self-hosted knowledge workspace for people who want linked notes, research material and AI writing tools in one place. Its block references let you connect individual passages rather than whole documents, with bidirectional links to follow those connections. It's open source under AGPL-3.0.

whisper.cpp runs OpenAI's Whisper speech recognition models on your own hardware, with fully offline transcription once you've downloaded a model. It's for developers building speech-to-text into applications and people who want to transcribe audio locally. Audio can stay on-device rather than going to a cloud transcription service. The project is open source under the MIT license.

Cline is an AI coding agent for developers who want help understanding a codebase and changing it. Its shared agent core is open source under Apache 2.0. You can use it in VS Code, JetBrains IDEs, or a terminal. A native desktop app runs on macOS and Windows. No editor is required for desktop sessions. The JetBrains plugin itself is not open source.

Docling is an MIT-licensed, open source document parser for developers turning files into structured content for search and AI applications. It runs locally on macOS, Linux, and Windows, including in air-gapped environments. Its PDF processing identifies page layout and reading order, extracts tables, code, and formulas, and classifies images.

LiteLLM gives platform teams one place to manage access to LLMs across providers. Its self-hosted AI gateway puts cloud services and internal or locally hosted models behind an OpenAI-compatible API, so applications can change models without changing their integration. Developers can also use its Python SDK directly.

Open WebUI gives individuals and teams a self-hosted place to chat with local LLMs and cloud models. It runs on your own computer or server, including through Docker, and can work entirely offline with local models.

Promptfoo is an open source CLI and library for testing prompts, AI agents, and RAG applications. It runs evaluations locally and helps developers compare model responses while security teams look for weaknesses in the applications built around them. The project is MIT licensed.

Screenpipe records screen activity and audio as searchable local history that AI agents can use as context. It's for people who want to recall past work and teams that want agents to draft follow-ups or update work records using what actually happened. Raw history stays on your device by default.

Wan2.2 is an open source family of video generation models for creators and developers who want to make clips on their own GPUs. Licensed under Apache 2.0, it covers text-to-video and image-to-video generation, with separate models for speech-driven video and character animation. Generation runs on your hardware when you use the downloadable models.

LangGraph is a free, MIT-licensed Python framework for developers building AI agents that need to keep state and handle complex tasks. It gives teams control over how an agent moves between steps, where people can intervene, and what happens when a long-running task is interrupted.

Fish Speech, currently featuring Fish Audio S2 Pro, is a self-hosted text-to-speech system for creators producing narration and developers building voice applications. It combines voice cloning with control over emotion and delivery within a script. Code and model weights use the custom FISH AUDIO RESEARCH LICENSE.

Goose is a general-purpose AI agent that runs on your computer. It suits people who want an agent for coding, research, writing, automation, or data analysis, without committing to one model provider. The desktop app runs on macOS, Windows, and Linux; there's also a CLI for terminal work and an API for use in other software.

MinerU parses documents locally into structured text for AI agents, RAG systems and knowledge bases. It's for people working with scanned PDFs, academic papers and Office files whose tables, formulas or page layouts need more care than plain text extraction.

Ollama runs language models on your own computer or server. It provides a command-line runner and a local API for people building AI applications or connecting existing tools to models they host themselves. The software is distributed under the MIT license.

SGLang is a self-hosted inference framework for teams that need to serve language and multimodal models on their own hardware. It runs on a single GPU or across distributed clusters and exposes an OpenAI-compatible API. The project is open source under the Apache 2.0 license.

Qwen3 is a family of language models from Alibaba Cloud’s Qwen team for people who want to run models locally or on their own servers. It spans smaller and larger dense models as well as mixture-of-experts models. The weights are publicly available.

Mem0 is a memory layer for developers building AI agents and assistants that need to recall earlier interactions. It retains user, session, and agent context across conversations, so an assistant can remember preferences or a support bot can refer to past tickets. The self-hosted code is open source under Apache 2.0; Mem0 also has a managed service.

VibeVoice is a family of MIT-licensed, open-source voice AI models for developers and researchers building local transcription or speech generation tools. Its speech recognition models combine transcript text with speaker labels and timestamps, so recordings retain information about who spoke and when.

rembg removes image backgrounds on your own hardware, with batch processing and a Python library for developers building image workflows. It's also useful for people preparing product cutouts or portraits who want control over processing and model choice. Local models keep images on your machine and can work offline once downloaded.

Transformers is a Python library for developers and researchers who want to run pretrained AI models or train their own on hardware they control. It covers language, images, audio, video and multimodal work through a shared way of defining models. The library runs in a local Python environment; pretrained checkpoints are available from the separate Hugging Face Hub.

Paperless-ngx is a self-hosted document management system for people who want to keep scanned paperwork in a searchable digital archive. It brings document scanning, indexing and storage together, so you can find records by their contents rather than sift through paper folders. You can run it on a local server at home, and it supports deployment with Docker.

LocalAI runs language models, speech, vision and image generation on hardware you control. It's for developers and teams that want a self-hosted AI server for their apps without sending model requests to a cloud service. Its OpenAI-compatible API works with existing clients, and it also accepts Anthropic, Ollama and ElevenLabs API calls.