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.

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.

TorchGeo is an open source Python library for machine learning researchers and remote sensing specialists working with satellite and aerial imagery. It brings geographic datasets and pretrained models into PyTorch training workflows. The MIT license allows you to use and adapt it for your own projects.

DSPy is a Python framework for developers building language model applications with local backends such as Ollama on a laptop or SGLang on a GPU server. It connects application code to those model servers, which handle inference on your hardware. It also supports cloud providers, so where model requests go depends on the backend you choose.

AI-Researcher automates research tasks for researchers who want to develop an idea into code, experiments and an academic manuscript. It can start with a detailed proposal or use reference papers to suggest a research direction.

PotPlayer ChatGPT Translate translates existing subtitles inside PotPlayer during video playback. It's for viewers who want AI translation with a choice of a local model or a hosted API.

Pretype is a local AI writing assistant for people who want sentence suggestions across their Mac apps. It works in native apps, Electron apps and web text fields without separate plugins for each app.

Fooocus generates images on your computer for people who want to work from prompts without extensive settings adjustments. It uses Stable Diffusion XL and works offline after the required models are downloaded.

Pi Messenger connects Pi coding agent sessions working in separate terminals on the same project. It's for developers who want agents to divide work, share progress and avoid conflicting edits.

ACE-Step is a local AI music model for musicians and producers who want to generate songs or revise existing audio. It accepts text descriptions and lyrics, with control over the length of the result.

TRL is a Python library for researchers and developers adapting foundation models with their own datasets. It builds on Hugging Face Transformers and supports training on a single GPU or across multiple machines.

llama-swap is a local AI proxy for people who want several models available to their apps without keeping them all loaded. It starts the server a request needs and replaces the active server when another model is requested.

VibeVoice is a family of voice AI models for developers and researchers building transcription and speech generation applications. It can capture who spoke and when, or produce spoken responses from incoming text.

Dia generates spoken English conversations from a written script. It's for developers and researchers who want to produce two-speaker dialogue on their own hardware, with audio references to guide the voices and delivery.

KoboldCpp runs language models on your own hardware for chat, creative writing and roleplay. It's a fork of llama.cpp with a bundled KoboldAI Lite browser interface.

YuE is an AI music generation project for songwriters, musicians and developers who want to create songs with vocals and accompaniment. Its YuE2 models produce an editable composition before rendering the audio, giving you control over the music behind the recording.

ARIA turns audio playing on a Windows PC into live subtitles for videos, games, browser playback and calls. It's for people who need captions across apps or want translations alongside the original speech.

ACP Bridge lets teams and bots access coding agents running on a development machine or server through a shared HTTP API. It connects agents through the Agent Client Protocol (ACP), so callers don't need each agent installed on their own computer.

GitHub MCP Server connects compatible AI assistants to GitHub so developers can ask about code and have an assistant act on repository activity. It's GitHub's official connector for the Model Context Protocol (MCP).

Image Toolbox is an Android photo editor for people who need to prepare images on their phone. It combines everyday edits with AI enhancement and tools for processing several images together.

Vespa is an AI search platform for developers building search, RAG and recommendation applications over large datasets that change continuously. It retrieves candidate results and evaluates their relevance with machine-learned models within the same platform.

Waifu2x-Extension-GUI is a Windows desktop app for enlarging artwork, photos and video with AI. It combines multiple processing engines in one interface for people working with both drawn and photographic media.

KTransformers is a research framework for developers running or fine-tuning large language models on their own hardware. It focuses on mixture-of-experts (MoE) models, using CPU resources alongside GPUs to work within limited GPU memory.

HD-BET uses neural networks to separate brain tissue from surrounding structures in MRI scans. It runs locally and is aimed at researchers and medical imaging teams who need automated brain masks, including for scans affected by tumors, lesions or surgical resection cavities.

Agno is a framework and runtime for developers building customer-facing or internal AI agents. It combines agent development, service hosting and a web interface for managing runs on infrastructure you control.

Mirrai is an AI companion for people who want to revisit unfinished conversations through a persona based on someone's chat history. It simulates their communication style, with a farewell process that gives the experience an optional endpoint.

Twinny is an AI coding assistant for developers who want completion and help with their repository inside VS Code, using models on their own hardware or a chosen server.

Claude Command Center helps developers keep track of coding agents working across multiple projects. It finds sessions launched in a terminal as well as through the dashboard, and agents keep running when you close it.

WayVoice is a local AI dictation app for Linux users who want to enter text by speaking in their desktop applications. It processes speech on your machine, with no cloud service required for recognition.

LLM Router is a self-hosted AI gateway for teams connecting applications to local LLM servers and cloud providers. It puts a shared interface in front of your models so clients can use the same gateway across backends.

Bifrost is an AI gateway for developers and teams building applications that use local LLMs or multiple cloud providers. It gives those applications a shared API for model access and a central place to manage usage.

FastGPT is an AI agent builder for teams creating document-based assistants and business workflows. It suits internal knowledge search, customer support and applications that combine answers with actions.

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.

FramePack is a desktop app for creating AI video from a still image and a written motion prompt. It's for people who want to animate images on their own hardware and inspect the clip while generation is still running.

opencodex is a local AI gateway for developers who want to choose which models power their coding assistants. It connects Codex, Claude Code, Claude Desktop and Grok Build to alternative providers while keeping each tool's native interface.

PanGuard AI checks skills and MCP servers for threats before AI agents load them, then watches their actions at runtime. It's for developers and teams who want protection against prompt injection, poisoned tools and malicious skills.

Scarf gives people running the Hermes AI agent a native interface for conversations, project work and host management. It requires an existing Hermes installation; the iPhone companion, ScarfGo, connects directly to your hosts over SSH.

olmOCR converts scanned and image-based documents into text for researchers and developers preparing LLM datasets. It handles pages whose layout makes ordinary text extraction difficult.

Kwipu helps people query a document folder or Obsidian vault and trace answers back to their notes. It connects information across documents so you can investigate project decisions, people and their roles, or relationships between ideas.

Atomic is a personal knowledge base for people who want to find connections across their notes and saved reading. It organizes Markdown notes, web clips, and articles into a knowledge graph you can search and explore.

Vibe is a desktop app for people who need transcripts or subtitles from recordings without uploading them to a transcription service. It handles audio and video locally, including interviews, meetings and material in different languages.

MiniCPM is a family of compact language models for developers building local assistants and coding agents. It targets on-device workloads and hardware with limited computing resources.

Scrypted connects home cameras to smart home apps and displays with low latency video streams. It's for people who want to use their cameras across different home systems or add recording through its NVR plugin.

Open Glean is a self-hosted AI workspace for searching files, notes, saved webpages and knowledge synced through Hydra DB connectors. Its browser app runs on your machine or server, including in Docker, but retrieval uses the remote Hydra DB API by default and requires a Hydra key. You can change the Hydra backend endpoint. Local answer models require explicit enablement and are disabled by default.

Cloak by Polyaura is an on-device AI app for people who want to chat and work with voice recordings on their iPhone or iPad without sending them to a cloud service. It works without an internet connection after the initial model download.

Marginalia is a research agent for people whose papers, notes and working files are spread across a mixed document library. It reads relevant parts of the original files before writing answers with citations.