Local & Self-Hosted AI Tools

Feeds Fun is a news reader for people whose RSS subscriptions produce more articles than they want to read. It assigns tags automatically, then uses rules you define to score articles by topic. You can self-host it with Docker or use the hosted service at feeds.fun.

Draw Things is an AI image generation app for iPhone, iPad and Mac that keeps generation on your device and works offline. It's for people who want to create and edit images without sending that work to a cloud service, including artists developing character concepts or trying out apparel designs.

BentoML is a Python framework for developers turning AI models into services on their own hardware or servers. It supports self-hosted inference APIs and multi-model applications, with Apache 2.0 licensing. You can develop and debug locally, then deploy the services in Docker containers, on Kubernetes, or in your own cloud.

LitGPT is a Python toolkit for developers and researchers who want to train, adapt and serve language models on their own hardware or servers. Its model implementations are written directly, with little abstraction between you and the code, so you can inspect model behavior and modify it for research or custom applications. It's open source under Apache 2.0.

OpenRLHF is a self-hosted Python framework for researchers and teams training language models with human feedback or custom rewards. It runs on your own NVIDIA GPU hardware, with Docker support and distributed training across servers. It's open source under Apache 2.0.

Dyad turns a written idea into a working web app on your desktop. It's for people who want to build without starting from code, as well as developers who want to keep control of the result. The app requires no sign-up and runs on macOS and Windows. Your project files stay on your machine.

SillyTavern is a locally installed LLM frontend for AI hobbyists who want detailed control over character chats and prompts. It builds on TavernAI as an independently developed fork and brings text models, image generation and voice into one interface. It's open source under AGPL-3.0.

LanceDB is an open source vector database for developers building AI retrieval applications and teams working with training datasets. Its embedded library runs locally or in your own cloud under the Apache 2.0 license. Cloud and Enterprise offerings provide managed infrastructure for production workloads.

Inbox Zero is an AI email assistant you can self-host with Docker or use as a hosted service. It's for people handling busy Gmail, Google Workspace, or Microsoft Outlook inboxes who want help sorting mail and preparing replies. It works alongside your existing email client.

Helicone combines an AI gateway with LLM observability for engineers building agents, chatbots, and document processing apps. You can self-host the open source observability platform under Apache 2.0 or use the hosted service. It also integrates with Ollama for apps that run models locally. Its hosted gateway routes requests to external AI providers, so those requests leave your machine.

Inspect AI is a Python framework for researchers and developers testing language models and AI agents. Developed by the UK AI Security Institute and Meridian Labs, it evaluates coding, reasoning, knowledge, behavior and multimodal understanding, including tasks where agents must take actions to succeed.

Hugging Face CLI is a terminal client for finding, downloading, and sharing models and datasets on the Hugging Face Hub. It's for developers working with local AI, model authors publishing their work, and coding agents that need access to Hub resources. The client runs on your machine and connects to Hugging Face's hosted platform.

LatentSync is an open-source AI lip-sync tool that edits a video's mouth movements to match supplied audio. It runs on your own GPU and suits video creators working with talking faces or virtual avatars, as well as researchers who want to train their own lip-sync models. The code uses the Apache 2.0 license.

LivePortrait animates a still portrait using facial expressions and head movements from a driving video. It's for creators who want to animate faces or edit motion in portrait videos on their own hardware. It works with realistic photos as well as portraits in oil paintings, sculptures and 3D renders.

MLC LLM is an open-source compiler and deployment engine for developers who want to run language models on their own hardware or inside apps. Its main distinction is the range of devices it targets: the same underlying engine, MLCEngine, serves desktop, browser and mobile deployments. The project uses the Apache 2.0 license.

Stagehand is an open-source browser automation SDK for developers building AI agents that interact with websites and extract structured data. It can run with Chrome on your own machine or use Browserbase's cloud browsers. Local runs require Chrome. The project uses the MIT license and supports TypeScript, Python, and Go.

Guidance is an MIT-licensed, open source Python library for developers who need language model output to follow a defined format. It works with local LLM backends including Transformers and llama.cpp, as well as OpenAI's cloud service. It's for application code.

Chatbox is an AI chat client for people who want local models and cloud providers in the same app. It connects to Ollama for local LLM use and supports GPT, Claude, Gemini, Grok and DeepSeek with your own API keys. Chatbox also offers its own hosted model service.

mistral.rs is an open source inference engine for running models on your own computer or self-hosted server. It's for developers building AI applications and people who want local chat, multimodal models and agent tools in the same runtime. The Rust project uses the MIT license.

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.

Garak is an open-source LLM vulnerability scanner for developers and security teams assessing models or dialogue systems. It tests local models as well as cloud services, so you can assess a model running on your own hardware or an application exposed through an API. The Python tool uses the Apache 2.0 license.

Nextcloud Assistant brings AI into Nextcloud Hub's documents, email, chat and calendar. It's for teams that want help with shared work while choosing where AI processing happens. With an on-premises model, data stays on your server. The app is open source under AGPL-3.0.

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.

TRELLIS is a local AI model for generating 3D assets from images or text prompts, aimed at 3D artists and researchers exploring asset creation. It can produce meshes, radiance fields and 3D Gaussians from the same underlying representation, so you can choose an output suited to your rendering or editing work.

Obsidian Copilot brings AI agents into your vault to find notes by meaning, edit drafts and organize research. It's for writers, researchers and other Obsidian users who want AI to work directly with their existing notes. Agents create Markdown files, wikilinks and canvases that remain in your vault.

DiffusionBee is an open-source AI art app for Mac users who want to generate and edit images on their own computer. It runs Stable Diffusion offline, with image generation processed on the device. Model downloads require network access, and optional image uploads can send images externally. Its visual interface suits artists and designers who want local image tools without working through code.

torchtune is a Python library for developers and researchers who want to adapt LLMs on their own GPU hardware using PyTorch. Its editable training recipes suit work that needs control over the training code and model implementations. The project is no longer actively maintained.

Elia is an open source terminal chat client for people who prefer a keyboard-focused interface to a browser chat app. It connects to local LLMs through Ollama or LocalAI and also works with hosted models such as ChatGPT and Claude. The interface runs on your machine; where prompts go depends on the model you choose.

Coze Studio is a self-hosted AI agent development platform for developers and teams building assistants and AI apps through visual, low-code tools. It brings agent creation, debugging and publishing into one workspace, with workflows for defining business logic. The open-source edition uses the Apache 2.0 license and shares its core engine with the commercial Coze Development Platform.

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.

Moondream is a vision model for developers building software that needs to understand images. It can answer questions about a picture, write captions, locate objects, identify points and segment regions. The open-weight models can run on your own hardware, including in an air-gapped environment. The repository code is licensed under Apache 2.0; check each model checkpoint’s own terms for use.

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.

Smart Connections is an Obsidian plugin that finds notes and passages related to what you're writing, even when you haven't linked them or entered a search query. It's for researchers, writers, and people whose vaults contain useful work they struggle to find again. Matches depend on meaning, so earlier research or a relevant decision can appear beside your current note without manual tagging.

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.

Letta is an open-source platform for AI agents that retain memory across conversations and use experience to improve over time. Formerly called MemGPT, it's for people building or using assistants that need continuity beyond a single chat. Agents can run locally or on a self-hosted server.

Stable Audio Tools is an MIT-licensed Python toolkit for developers and audio researchers who want to generate audio on their own hardware or train models on their own recordings. It combines model inference with training and fine-tuning, so you can work with pretrained models or build a model around a specific audio dataset.

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.

YuE is an open-source music generation project for musicians, songwriters and developers who want to turn lyrics and a style prompt into songs with vocals and accompaniment. Its YuE2 models create an editable melody and chord score before generating the recording, so you can review the composition and change musical details before hearing the result.

DSPy is a Python framework for developers building AI applications whose tasks need clear inputs, predictable output types, and measurable results. You define what a language model should produce, then compose those tasks into a larger program. It's open source under the MIT license.

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.

Llama is Meta's family of large language models for developers, researchers and businesses that want to run models on their own hardware or servers. Its downloadable weights let you build generative AI applications with local inference. Access requires license acceptance and approval, and the weights use custom licensing for research and commercial use.