Local & Self-Hosted AI Tools

Comfy Desktop runs ComfyUI's node-based generative AI workflows on your own hardware. It's for creators who want to build image and video workflows without managing Python dependencies themselves.

MaxKB is an AI agent platform for organizations building support bots, internal knowledge assistants and business automation. It combines answers based on company documents with workflows that can act through connected tools.

Wingman-AI is a self-hosted AI agent platform for developers and teams handling coding, research, operations or support tasks that need ongoing context. It coordinates agents with distinct roles and retains their sessions across clients.

PrivateGPT is a self-hosted API layer for developers building applications around local models. It requires a separate inference server, such as Ollama, llama.cpp, vLLM or LocalAI; it doesn't run models itself.

Webcmd is a browser automation tool for developers whose AI agents repeatedly work with the same websites. It keeps what agents learn locally so later tasks can use familiar workflows instead of inspecting each site from scratch.

taOS is a self-hosted AI agent platform for people who want to run assistants on their own computers and keep their conversations, files, and memory there. It brings agent management and local model access into a browser-based desktop.

Stable Audio Tools is a Python toolkit for developers and audio researchers who want to generate audio or train models on their own recordings. It supports work with pretrained models as well as training from scratch.

TeroSubtitler helps subtitlers, translators and video creators prepare captions for video content and streaming services. It combines automatic audio transcription with tools for editing text, adjusting timing and checking subtitle quality.

1Panel is a Linux server management panel for people hosting AI software alongside websites and other applications. Its browser interface brings model and agent management together with everyday server administration.

Faceswap replaces faces in photos and videos using deep learning. It's for VFX artists, hobbyists and researchers who want to train face-swapping models on their own material and run them locally.

Reticle lets AI coding agents check changes against a running web or desktop app. It's for developers who need to catch failed requests, duplicate submissions and application state that disagrees with what the screen shows.

Local Deep Research is a self-hosted AI research assistant for people investigating complex questions across web sources, academic papers and their own documents. It gathers evidence and writes reports with citations.

CleanRL is a Python deep reinforcement learning library for researchers and developers who want to study or modify an algorithm without tracing it through a large modular codebase. Each algorithm variant lives in one standalone file. Experiments can run locally, while Docker and AWS integration support cloud execution through AWS Batch.

QwenPaw is a personal AI assistant for people who want an agent on their own computer or server. It retains conversation history and a personal knowledge base across sessions.

AutoGluon is a Python AutoML library for developers and data scientists who want predictive models without selecting every algorithm themselves. It chooses combinations of classic machine learning and foundation models for the task.

Joplin Jarvis is an AI assistant for people who keep their research and writing in Joplin. It uses your notes as context for conversations and helps you find related material or annotate your collection.

Talkio puts several AI models in one conversation so you can compare answers or have different roles discuss the same problem. It also supports ordinary one-to-one chats.

aichat is a terminal AI assistant for people who want to discuss files, generate shell commands and use model-powered tools from the command line. It connects to Ollama, OpenAI, Claude, Gemini and OpenAI-compatible API providers.

IntraPaint is a desktop image editor for people who want manual painting and AI edits in the same application. It combines conventional image editing tools with image generation and inpainting, which lets you use AI to replace parts of an existing image.

GPT-SoVITS is a local voice cloning and text-to-speech tool for people creating speech in a custom voice. Its web interface covers speech generation, voice training and preparation of audio datasets.

Alexandria Audiobook turns books into audio with separate narrator and character voices. It's for people who want to choose the cast and correct individual passages before exporting an audiobook.

Arize Phoenix helps developers investigate failures in AI agents and LLM applications and compare proposed fixes. It connects recorded application activity with evaluations and repeatable experiments.

Apache Burr is a self-hosted Python framework for developers building AI agents, chatbots, and other applications with branching decisions. It models application logic as a state machine, so developers can see which action ran, what changed, and why execution took a particular path. Its library and monitoring UI run on your own infrastructure, and its open-source code uses the Apache 2.0 license.

MiniMind is a toolkit for learners and developers who want to understand language models by training small ones on their own hardware. Its core training algorithms use native PyTorch code that you can inspect and change.

Bloks is a desktop workspace for people who want personal AI agents working on their own computer. Its messaging-style interface gives agents individual chats and shared rooms for collaborative work.

Wyoming Protocol connects Home Assistant with separate voice services. It's for developers and people assembling a voice assistant who want to choose their own transcription, speech synthesis, and wake word components. Connections have no authentication or encryption, so it requires a trusted network.

Mooncake provides storage and data transfer components for teams running distributed LLM inference. Its Transfer Engine and Mooncake Store support shared caching and deployments that separate prompt processing from token generation.

insanely-fast-whisper is a command-line audio transcription tool for people who want to process recordings on their own hardware. It focuses on reducing transcription time through GPU acceleration.

Ultralytics YOLO is a Python computer vision library for developers building applications that interpret images and video. Models can run on hardware you control for tasks such as visual inspection, inventory monitoring and robotics perception.

AgentGUI gives researchers and developers a visual workspace for supervising long-running AI agents. Its pixel-art office represents tasks as desks, so you can follow several jobs and intervene while they run.

Wispuh is an MIT-licensed speech-to-text app for macOS 14 and later that puts dictated text into the app you're working in. It's for Mac users who want voice input across their everyday software without sending recordings to a cloud service. It doesn't require an account.

Accentize dxRevive is a proprietary AI speech restoration plugin for macOS and Windows that reconstructs missing frequency content as well as reducing noise. It's aimed at podcast editors, content creators and dialogue editors working with damaged or poorly recorded speech. All audio processing stays on your computer, without cloud uploads or special hardware.

Pieces builds a searchable history of your work across apps for people who need to recover earlier decisions, find research or pick up an interrupted task. It runs in the background on your computer.

Talon Voice lets people write, code, browse and play games through hands-free computer input. It suits people who want to control their computer using speech, eye movements or sounds.

gptme is an AI agent for developers and people doing data analysis or other knowledge work in their own environment. It can act on files and use installed tools, with a choice of local models or cloud providers.

LLMux is a self-hosted AI gateway for developers who want to use local models and cloud providers through one interface while controlling where requests go. It blocks remote inference by default and logs permitted calls that leave the machine.

LLMStack is a self-hosted no-code builder for teams creating AI agents, chatbots and workflows around their own data and business processes. You can run it on your own infrastructure or use Promptly, its hosted cloud offering. Self-hosting runs the platform on your server; connected cloud model providers process requests outside it.

Onyx is an AI search and chat platform for teams with information scattered across workplace apps. It gives employees and AI agents answers grounded in company documents.

SuperClaude is a configuration framework for developers who want predefined workflows in Claude Code. It adds task-specific commands and specialist agents for planning software, writing code and reviewing the results.

KittenTTS is a Python text-to-speech library for developers adding local speech generation to apps or producing spoken audio from text. It supports voice cloning without model training and doesn't require a GPU.

Ragpi is a self-hosted AI assistant API for teams that want to answer technical questions using their own project material. It lets developers add documentation-based support to a product, website or community.

FlashMLA is an attention library for developers building DeepSeek-V4.1 inference systems on their own hardware. It requires NVIDIA SM100 or SM103 GPUs, or Huawei Ascend 950 NPUs.

AI Runner is a desktop app for people who want an AI companion and an art workspace on their own hardware. Its local chat, voice and image tools work offline without an API key or subscription.

Diariz is a self-hosted meeting transcription app for individuals and teams that want recordings and transcripts on their own server. It turns captured or uploaded audio into searchable meeting records.

AVCLabs Video Enhancer AI is a paid desktop app for restoring and upscaling video on Windows and macOS. It suits people working with home movies, documentary archives, or footage affected by blur and compression. Video processing runs offline on your computer, and your files stay there. AVCLabs also offers a separate cloud upscaler for entry-level devices.

Open WebUI is a self-hosted chat workspace for individuals and teams using local LLMs and cloud models. It can work entirely offline with local models.