Local & Self-Hosted AI Tools

Speech Note lets you dictate, read aloud and translate multilingual notes on Linux and Sailfish OS. It's for people who want speech and text processing to stay on their device and work offline.

FinGPT is a financial LLM framework for researchers and developers building tools that interpret market news and company information. It includes trained models, financial datasets, and tools for adapting models to specific finance tasks.

Transcribro lets Android users dictate text with speech recognition running on their device. It supports English only and can also provide transcription to compatible apps.

Neo4j LLM Graph Builder converts documents and web content into knowledge graphs for people building searchable collections or AI applications with Neo4j. It uses an LLM to identify entities, relationships, and their properties.

CopilotKit is a self-hostable SDK for developers putting AI agents inside their apps. Its open-source SDK uses MIT, and its enterprise runtime and Intelligence platform can also run on your infrastructure. Copilot Cloud provides managed hosting; where model requests go depends on the agent backend you connect.

Dory is a native macOS app for developers who want containers, Linux machines and coding agent environments on their own Mac. It provides a local runtime managed through both a graphical app and a CLI.

VACE is an AI video model for creators and developers who want to generate footage or edit existing clips locally. It combines reference-based generation and video editing, including changes limited to masked areas.

Voicetypr is a desktop dictation app for people who write emails, code, prompts, or notes throughout the day. It inserts speech as text wherever your cursor sits, including in Slack, Gmail, Cursor, and Notion. Local transcription works offline, with your recordings and transcripts staying on your machine. The source code uses the AGPL-3.0 license; the desktop product is paid.

Stable Diffusion 1.5 is an AI image generation model for artists and developers who want to create artwork or explore design ideas on their own hardware. It can start with a text prompt or modify an existing picture.

Next AI Draw.io turns written descriptions and uploaded files into diagrams you can edit on a draw.io canvas. It's for people creating technical diagrams who want AI help with drafting and revisions while keeping control of individual shapes.

MinerU is a local document parser for people preparing files for AI workflows. It handles scanned PDFs, academic papers and other documents containing OCR text, tables, figures or complex layouts.

SDMetrics is an open source Python library for people who need to assess synthetic tabular data before using it in software testing or machine learning development. It compares generated datasets with the real data they're meant to resemble. It works with data from any model, so your choice of generator doesn't determine how you evaluate the results.

Viseron is a self-hosted network video recorder for people monitoring a home, office or other property. It combines camera recording with AI analysis that runs on your own hardware.

Stability Matrix is a desktop app for people who want to use several Stable Diffusion interfaces with one model library. It manages local Web UI packages and includes its own interface for generating images.

WhipCode is an open-source coding agent for developers tackling jobs that exceed a single model context window. It lets agents divide the work while you follow their progress and send further instructions.

Offeline is a local AI chat app for people who want to talk to AI on their phone or tablet without sending conversations to a hosted chatbot. It processes chats on the device.

Gemma is Google DeepMind's family of open-weight AI models for developers building applications on their own hardware. It includes compact models for mobile and IoT devices and larger models for reasoning on personal computers and servers.

nerd-dictation turns speech into text for people who want voice input in their Linux applications. It runs recognition locally with VOSK and works offline, with command-line controls for dictation.

Moonshine is an on-device AI toolkit for developers building voice agents and spoken interfaces. Voice processing runs on the device without an account or API keys.

BGE Embeddings is a family of models for developers who need to find relevant passages for search or retrieval-augmented generation (RAG). It includes embedding models for finding candidate text and rerankers for assessing how closely those results match a query.

Maat Agent is a coding assistant for developers who want testable evidence before accepting AI edits. It runs in a terminal or an Electron desktop app on macOS, Windows and Linux, and checks the actual project files against acceptance criteria set before work begins. Failed checks send their output back to the model for another attempt; if the work still fails, the agent reports failure.

Argos Translate translates text on your own machine for people who need offline translation and developers adding translation to their software. Once you have the language models, it can translate without an internet connection or sending text to an online service.

TaxHacker is a self-hosted AI accounting app for freelancers, indie hackers, and small businesses that need to turn receipts and invoices into searchable transactions. The project is in early development. Its open source edition runs on your own infrastructure or home server through Docker and uses the MIT license.

Off Grid AI is a local AI app for people who want chat, document analysis and media tools on their own phone or computer. Downloaded models work offline, and the core app doesn't require an account.

Starcat is a native macOS app for developers who want to find and evaluate repositories they've saved on GitHub. It keeps a local library and lets you choose which repositories enter a private AI knowledge base.

DeepReg is an open-source Python toolkit for researchers and educators studying medical image registration with deep learning. It brings together algorithms for aligning medical images, with an emphasis on clinical applications and methods that use limited supervision.

dots.ocr is a self-hosted OCR model for developers and teams that need text and page structure from multilingual documents. It combines text recognition and layout parsing in a single vision-language model you can run on your own hardware.

Quivr is a content search and monitoring engine for developers building applications around incoming material and topics they want to follow over time. It's at an evaluation stage, and the project advises against production use because its API may change without notice.

Moshi is a voice AI model and dialogue framework for researchers and developers building spoken applications. It processes speech directly and can listen while it speaks, including information such as emotion and non-verbal cues.

GPTQModel is a Python toolkit for developers compressing LLMs and running them on their own hardware or servers. It combines model preparation, quality evaluation and inference so you can assess compression choices within one workflow.

Dream Textures is a Blender add-on for artists who want to generate image assets and texture 3D scenes without leaving Blender. It runs Stable Diffusion on your machine and uses scene depth to guide texture projection.

Kohya's GUI is a browser interface for training image generation models, aimed at artists and model makers who want to teach a model a style or subject. It builds on Kohya's Stable Diffusion training scripts and also provides a command-line interface.

Steel is a browser API for developers building AI agents that interact with websites. It supplies real Chrome sessions for tasks involving clicks, forms, logins and pages that rely on JavaScript.

Skales is an AI agent for people who want help with files, browsing, email and coding on their own devices. It can keep working on a goal after you close the chat and resume unfinished goals after a restart.

Pi Web is a browser workspace for developers using the pi coding agent. It shares pi's local conversations and configuration, so you can resume the same coding work in either interface.

Agent Pilot is a desktop AI workflow builder for people who want to combine model conversations with tools and code. It runs on Windows, Linux and Intel Macs and is open source under AGPL-3.0. You can chat with one model or build a graph of cooperating agents, with human input included where a task needs it.

EasyOCR is a Python library for developers adding text recognition to an application. It reads both text in photographs and dense document text.

Devo is a coding agent for developers who want to choose their model provider and run the agent on their own machine. Its desktop app and terminal interface handle coding and other engineering tasks that require multiple steps.

PaddleDetection is a computer vision toolkit for developers building image and video analysis systems. It covers training, adapting and deploying models for uses such as inspection and traffic analysis.

Clippinator is a Python AI coding assistant that runs on your machine while its agents use GPT-4 through OpenAI's cloud API. It's for developers who want to delegate project work and review the results as it proceeds. It requires an OpenAI API key and internet access, so model processing happens in the cloud rather than on your hardware.

Gitingest prepares code context for developers who want to give an LLM a repository or local directory. It gathers the project structure and file contents into a text digest instead of requiring you to assemble files by hand.

iZotope Neutron is a proprietary audio mixing suite for producers, musicians and mix engineers who want an assisted starting point and control over individual effects. Its AI-powered Mix Assistant helps shape a mix, while manual controls let you build your own processing chain.

WindsurfAPI, also called DevinAPI, connects coding assistants and other AI clients to models through your own Devin account. The gateway runs on your hardware, but it sends prompts and images to Devin's cloud for inference, so it requires internet access.

SmolVLM is a compact vision language model for developers building applications that interpret images and answer questions about them. It can run on-device, including on laptops and smaller local setups.

Typebot is a visual builder for businesses creating chatbots and conversational forms for websites, mobile apps and WhatsApp. You can host it on your own server or use its managed cloud service.

Photomator is a paid photo editor for Mac, iPhone, iPad, and Vision Pro that combines manual color controls with machine learning tools. It's for photographers who want to edit RAW files, retouch individual shots, and apply consistent adjustments across a photo collection within Apple's native apps and file system.