Local & Self-Hosted AI Tools

Hope Agent is a desktop AI assistant that can also run without a desktop interface on a NAS or cloud server. It's for people who want ongoing project work, memory and task state to carry across sessions and devices. It supports local model setup. Data stays on the hosting machine by default, while requests to remote models go directly to the selected provider.

Anakin is a web scraping API for developers feeding website content into AI agents, RAG pipelines, or data extraction workflows. You can run its scraping engine on your own server or use the hosted service.

Strands Harness SDK is an open source toolkit for developers building AI agents who need control over their behavior. It handles the agent loop while letting you choose its components.

Top2Vec is an open-source Python library for researchers and developers who want to discover themes in text collections and search documents by meaning. It determines the number of topics automatically and connects topics, documents and words through a shared embedding space. The license is BSD-3-Clause.

OpenScribe is an AI medical scribe for clinicians who want to turn recorded patient encounters into structured draft notes. Its desktop workflow builds on StenoAI and keeps transcription and note generation local. It's not HIPAA compliant, and every generated note requires clinical review.

Excire Foto is a desktop photo and video manager for enthusiast and professional photographers sorting through shoots or searching large archives. Its AI analyzes photos on your computer without uploading them for analysis.

VoxCPM is a local text-to-speech system for developers and audio creators who want to generate speech with voices they can design or clone. It supports multilingual narration and control over how a voice delivers the text.

Open Sora Plan is a video generation project for researchers and developers who want to work with model checkpoints on their own hardware. It aims to reproduce capabilities of OpenAI's Sora, with text-to-video and image-to-video models.

FlashRank is a Python library that runs reranking models locally on CPU, without Torch or Transformers. It's for developers building search systems or retrieval-augmented generation (RAG) apps who want to reorder retrieved passages by relevance before passing them to an LLM.

Witsy is a desktop AI assistant for people who want to chat with models, work with documents and write across applications. You can choose local models or cloud providers, with feature availability depending on the backend.

PDFMathTranslate translates scientific papers for readers who need the text in another language while keeping equations and figures in context. It produces translated and bilingual PDFs so readers can compare the result with the original.

InfiniteYou generates images from a reference face and a text prompt while preserving the person's facial identity. It's a local AI framework for researchers studying personalized image generation, with model use restricted to academic research.

Braina combines AI chat, dictation and computer control for people who want to work through spoken or typed commands. It can run language models on your own computer and help with writing, document research and repetitive desktop tasks.

RTK filters command output before an AI coding assistant reads it. It's for developers whose agents spend too much context on build logs, passing tests and repetitive terminal output.

Home Generative Agent is a Home Assistant integration for people who want to control their smart home through conversation and get alerts about security issues. It can use fully local models, so home data doesn't have to leave your network.

Whisper ASR Webservice gives developers a speech-to-text API for their own applications and services. It processes audio on your machine or server and supports multilingual transcription, speech translation and language identification.

Sillage is a self-hosted web interface for developers who want to control Claude Code, Codex and OpenCode from a computer or phone. It runs the native agent CLIs on your machine with their own tools and permission flows. Agents use your existing subscriptions and API credentials; hosting the interface doesn't replace their model providers.

Pi is a terminal coding agent for developers who want an assistant they can adapt to their projects. Its small core supports custom workflows through extensions and shareable packages.

Postgres MCP Pro gives AI assistants access to PostgreSQL databases and tools for investigating performance problems. It's for developers and database maintainers who want an assistant to work with actual schema details and query plans.

Ray Serve is a Python library for developers building inference APIs around machine learning models. It's useful when a response needs several models or application steps, rather than a single model call.

Meetily records calls and turns them into live transcripts and meeting summaries. It's for people who want to keep meeting recordings on their own computer without adding a recording bot to the call.

QOwnNotes is a desktop notepad and todo manager for people who want to keep their notes in ordinary Markdown files on their own computer. It can use existing text files directly, so your notes remain accessible outside the app.

ReadAny is an AI e-book reader for people who want to question a book, find an idea they remember imperfectly and keep notes alongside their reading. It combines a personal library with answers tied to book passages.

FiftyOne is a local tool for computer vision teams that need to inspect their training data and understand where their models fail. It runs on macOS, Windows and Linux, with Docker support, and is open source under Apache 2.0. Its Python tools and visual App connect dataset curation with model evaluation.

Brave Leo is an AI assistant inside the Brave browser for people who want help with what they're reading. Bring Your Own Model support lets you use a local LLM or a remote model for browser conversations.

MacParakeet is a speech-to-text app for people who want to dictate across Mac apps, transcribe recordings and capture meetings while keeping speech recognition on their own hardware.

EmbedAnything is a local embedding pipeline for developers building semantic search and retrieval-augmented generation (RAG) applications. It turns documents and media into vectors for indexing in a vector database.

Amuse is a Windows app for people who want to generate media and text with models running on their own hardware. It combines generation with editing tools for both generated output and existing local video.

NeuralForecast is an open-source Python library for data scientists and developers who want to train and compare neural time series forecasting models in their own Python environment. It brings recurrent networks and forecasting-specific architectures under one interface, so comparing models doesn't require working with separate research implementations. The license is Apache 2.0.

Liza coordinates AI coding agents for developers who want to delegate software work while keeping control over goals and constraints. It supports human-led pairing and multi-agent delivery runs that can proceed unattended.

ON1 Photo RAW is a desktop photo editor for photographers who want to manage and edit RAW photos in one application. It combines a photo browser with retouching and layered editing, covering work you might otherwise split between Lightroom and Photoshop.

torchtitan is a training platform for researchers and developers experimenting with generative AI models on their own GPU servers or clusters. Its replaceable components and extension points support work on model architectures and training infrastructure.

MemMachine gives developers building AI agents a way to remember earlier conversations and user preferences. Its memory persists across sessions, agents and model changes, so user history can carry over when an application switches models.

ggml is a library for developers building machine learning runtimes and local AI applications. It provides tensor computation across different kinds of hardware; GGUF is the model file format covered by the project.

BoltAI is an AI workspace for Mac users who want local models and cloud services in one app for writing, coding and research. It keeps related conversations together and brings chat into other apps through an overlay.

Purple is a desktop AI assistant for Linux and macOS that lets Ollama models carry out tasks on your computer. It's for people who want chat alongside shell commands, file operations and longer tasks they can review before execution.

GooeyPi gives developers a desktop interface for working with Pi, OMP and Prime Agent on local coding projects. Each agent keeps its own models, credentials and sessions, and switching agents doesn't stop work running in another.

CodePilot is a desktop AI workspace for coding, project work and everyday tasks. It brings Claude Code, Codex and a built-in agent into one app for people who want to work with files and conversations across local models and cloud services.

Klee is a native macOS AI chat app and agent for people who want an assistant to work with files on their Mac. It runs models locally through MLX, and downloaded models can chat offline without an account or API key.

MLX LM is a Python package for developers and researchers who want to generate text and adapt language models on Apple Silicon Macs. It uses MLX for local inference and training, with access through Python or a terminal.

Paperless-ngx is a document management system for people who want a searchable archive of their scanned paperwork. It helps keep records such as invoices and tax documents available without searching through paper folders.

Morphik Core is a retrieval engine for developers building AI applications around documents whose meaning depends on charts, diagrams, or page layout. It brings document search and structured extraction into one platform.

Phi-4 is Microsoft's language model for developers building applications that need complex reasoning and math problem solving. It can run on your own hardware without a cloud connection.

Agentic Orchestrator coordinates coding agents for engineers supervising feature work across one or more repositories. It keeps requirements, design decisions and verification evidence attached to the work as it moves toward a reviewable pull request.

SkyRL is a Python library for researchers and developers who want to train LLMs with reinforcement learning on their own hardware. Its Tinker API support lets you run existing Tinker training scripts against a server you control without changing the scripts. It's open source under Apache 2.0.

Stable Baselines3 is a Python library for training reinforcement learning agents on your own hardware using PyTorch. It builds on Stable Baselines and gives researchers and developers tested algorithm implementations for comparing approaches or building their own projects. It's free and open source under the MIT license.