Local & Self-Hosted AI Tools

dstack is a self-hosted orchestration tool for AI teams managing compute across GPU clouds and their own servers. It puts cluster management, training jobs and model inference behind one interface, so teams can use different providers and accelerators without maintaining a separate workflow for each environment. It's open source under the Mozilla Public License 2.0.

rclip searches image folders by their visual content, so you can find photos without adding tags or importing them into a photo library. It's a local AI tool for people who keep image collections on their own computers or servers and prefer working in the terminal. It runs on Linux, Windows and Apple Silicon macOS, and it's open source under the MIT license.

jetson-containers is a Docker container build system for developers running local AI and robotics workloads on NVIDIA Jetson hardware. It supplies prebuilt images and lets you combine AI packages into custom containers, reducing the work of assembling compatible GPU software for JetPack/L4T.

Home-LLM connects Home Assistant to language models running on your own hardware, so you can control smart devices through voice or chat. It's for Home Assistant users who want natural language control without relying on a cloud service or subscription. The project pairs a custom integration with small models trained specifically for smart home commands.

Kodus is an AI code review tool for engineering teams that want automated pull request feedback while choosing where the reviewer runs and which model it uses. Its open source core uses the AGPL license and can be self-hosted with Docker Compose or on Kubernetes. Kodus also offers a hosted cloud service that manages the infrastructure.

gollama is a terminal app for people managing a local LLM collection in Ollama on macOS or Linux. It puts model details and management actions in one keyboard-driven view, useful when you need to compare downloaded models or clear out ones you no longer use. It's open source under the MIT license.

LabelMe is a desktop image annotation app for people preparing computer vision datasets. It combines manual drawing with AI assistance for outlining objects and creating labels from text. It runs on 64-bit macOS, Windows and Linux..

llmcord is a self-hosted Discord bot for people who want to share LLM conversations with friends or a community. You can run the Python bot on your own machine or server, including through Docker, and connect it to local models or cloud providers. It's open source under the MIT license.

LocalWriter brings local LLM writing assistance into LibreOffice Writer for people who want to draft and revise text inside their documents. It runs on macOS, Windows and Linux and connects to a separate model runner, including Ollama and text-generation-webui. With a backend on your own machine, text processing stays local.

PowerInfer is a local LLM inference engine for developers and researchers who want to run large models on a PC with a consumer GPU. It splits work between the CPU and GPU to reduce GPU memory demands and data transfers. The code is open source under the MIT license.

GPT-SoVITS is a local text-to-speech and voice cloning tool. It can generate speech from a short reference recording or fine-tune a model for a custom voice. The source code uses the MIT license.

SurrealDB is a self-hosted database for developers building AI agents, knowledge graphs and applications that need several kinds of data together. It stores documents, relationships, vectors and time-series data in one engine, so an application's records and its AI retrieval layer can share the same database.

OpenVoice is an open-source voice cloning tool that uses a short recording to reproduce a speaker's voice in generated speech. It's for developers and creators who need a recognizable voice across languages, with control over how that voice sounds. The Python project is MIT licensed for commercial use.

Postgres MCP Pro is a self-hosted MCP server that gives AI assistants access to PostgreSQL alongside tools for diagnosing slow queries and testing index recommendations. It's for developers and database maintainers who want their assistant to work with the database's actual schema, query statistics and execution plans. It runs through Docker or Python and is open source under the MIT license.

Reins is an open-source chat app for people using self-hosted LLMs through Ollama. It runs on iOS, Android, macOS, Linux and Windows, giving Ollama users a mobile and desktop interface for experimenting with models. Reins is the client; Ollama provides the model backend.

Voice Changer (w-okada), also called VCClient, converts your voice as you speak using AI voice models. It's for people who want live voice conversion on their own computer, including those recording gaming commentary while running demanding software. Processing can stay local.

SadTalker generates talking head videos from a single portrait and an audio recording. The project states an Apache 2.0 license and removal of its earlier noncommercial restriction. It runs locally on Windows, Linux and macOS, and suits creators who want to animate a face without recording a person on camera. Its animation includes facial expressions and head movement, with examples covering speech and singing in different languages.

OpenVoiceOS is a free, open-source voice AI platform for people building their own smart speakers or adding voice control to devices. Its core builds on a fork of MycroftAI/mycroft-core, and most classic Mycroft skills also work with it. The project uses the Apache 2.0 license, which permits personal and commercial use.

Blue Iris is paid video security software for people managing cameras at home or across business premises. It runs on a Windows PC and includes built-in AI services, so AI processing doesn't require a separate external server. It combines camera recording with remote viewing and controls.

GitHub MCP Server is GitHub's official connector for developers who want their AI assistant to work with repositories and project activity. It gives compatible coding assistants access to GitHub through the Model Context Protocol (MCP), so they can retrieve context and take actions requested in natural language. The code is open source under the MIT license.

Open Interpreter is a terminal coding assistant built around open-weight models, with model-specific behavior for Kimi, Qwen and DeepSeek. It's a fork of OpenAI's Codex for developers who want to choose their model provider while keeping a familiar agent interface. The project uses the Apache 2.0 license.

Wyoming Protocol connects Home Assistant with separate voice services on a trusted network. It's for developers and people assembling a self-hosted voice assistant who want to choose their own speech recognition, speech synthesis and wake word components. The Python project is open source under the MIT license.

DeepTeam is a Python framework that runs locally to test chatbots, AI agents, and retrieval-augmented generation (RAG) pipelines for security and safety failures. Built on DeepEval, it's open source under Apache 2.0 and aimed at developers and security teams assessing AI applications before deployment or during ongoing development.

MetaGPT organizes AI agents into a software development team, with roles for product management, architecture, project management and engineering. It's a self-hosted Python framework for developers who want to generate software projects from plain-language requirements or build their own collaborative agents.

LiveKit Agents is a framework for developers building voice assistants, phone agents, and apps that combine speech with video or text. Agents join LiveKit rooms as participants, so they can interact with people through web and mobile apps or telephone calls. The Apache 2.0 project lets you run the entire stack on your own servers, including the LiveKit media server.

GOT-OCR2.0 is an OCR model for developers and researchers who want to extract text from images on their own hardware. It handles both plain text and formatted output through a single model, with recognition modes for selected regions and documents spanning multiple pages. The Python codebase builds on Vary.

CAMEL is an open-source Python framework for developers and researchers building systems where AI agents work together. Its focus is on agent roles, communication, and behavior across extended tasks, with applications in synthetic training data, task automation, and simulated societies. It uses the Apache 2.0 license.

Rasa is an AI agent platform for product teams building customer-facing text and voice assistants. Teams can deploy agents on their own infrastructure and choose their models and data arrangements. Its CALM engine combines language model understanding with business flows whose code enforces rules, so an assistant can handle conversational wording while following defined processes.

Petals lets developers and researchers use large language models that won't fit on a single consumer GPU by sharing the work across a network of machines. It supports text generation and fine-tuning from a desktop computer or Google Colab. Each participant holds part of the model, while other computers handle the remaining parts.

ECC is a free, MIT-licensed open source toolkit that adds repeatable engineering workflows to coding assistants. It runs alongside your chosen agent and works with self-hosted models or cloud providers through that agent's supported endpoints. It's for developers who want planning, testing and review to follow a consistent process across coding sessions.

any-llm is a Python library for developers who want the same application to work with local LLM servers and cloud providers. It connects to Ollama and custom OpenAI-compatible endpoints, alongside OpenAI, Anthropic, Mistral and Azure / Microsoft Foundry. A shared interface reduces the provider-specific code needed to try another model or change where inference runs.

TruLens is an open-source Python tool for developers who need to find why an AI agent gives a wrong answer or spends too much on a task. It pairs step-level traces with evaluation scores, so you can connect failures to retrieval, reasoning or tool calls. It uses the MIT license and can write results to a database you run.

Chrome DevTools MCP gives AI coding assistants access to a live Chrome browser through a locally running MCP server. It's for developers who want their agent to inspect how a web app behaves, investigate errors and measure performance alongside its coding work. It works with clients such as Claude Code, Cursor, Copilot and Antigravity.

DeepFace is a Python library for developers building face recognition into their own applications. It runs locally or as a self-hosted API, including through Docker. A separate managed API at deepface.dev handles processing on hosted infrastructure. The library is open source under the MIT license.

Parakeet is NVIDIA's speech recognition model family. The linked parakeet-tdt-0.6b-v2 is its English speech-to-text model for developers and researchers building transcription services, subtitles or voice applications. It runs locally through NeMo on Linux, with NVIDIA GPUs recommended for inference. It's a model you can embed in an application, rather than a desktop transcription app.

DeepSeek-OCR is an open-source OCR model for developers building document processing tools and researchers studying how AI reads text through images. It runs on your own hardware with NVIDIA CUDA GPUs. Its distinctive focus is visual text compression: representing document images with compact sets of vision tokens for a language model to read.

rerankers is a Python library for developers building search and retrieval systems who want to compare reranking models without rewriting their integration each time. It takes a query and candidate documents, then ranks their relevance through a shared interface across local models and hosted services. It's open source under Apache 2.0.

Distil-Whisper is a family of local speech recognition models for developers building English transcription into their apps or services. It reduces Whisper's size and processing time while retaining much of its transcription accuracy. It supports English only.

PDF-Extract-Kit is a local AI model toolbox for developers and researchers building document processing applications. It extracts text, tables and mathematical formulas from PDFs, with separate models for identifying page elements and recognizing their contents. It's open source under AGPL-3.0, written in Python, and supports CPU or GPU execution on your own hardware.

Text Generator is an MIT-licensed Obsidian plugin for generating ideas, titles, summaries, outlines and paragraphs using your notes as context. It supports local models as well as OpenAI, Anthropic, Google and Hugging Face.

gpustat is a local command-line GPU monitor for people running AI models or other workloads on NVIDIA hardware. It puts GPU activity and the processes using each device into a compact terminal view, useful when you need to check memory use or see who’s occupying a shared GPU. It's open source under the MIT license.

Cactus is an on-device AI engine for developers building automation into mobile apps, wearables and embedded devices. Its Needle model handles tool calling locally, so a device can turn a request into an action without an internet connection. The focus is small devices, including smart home hardware, robots and microcontrollers.

mcpo makes MCP tools accessible to AI agents and apps that accept OpenAPI servers, including Open WebUI. It's a self-hosted proxy for developers who want to use existing MCP servers with those apps without writing a separate adapter for each tool. You can run it locally or on your own server with Python or Docker. It's open source under the MIT license.

TensorBoard is a browser-based toolkit for inspecting TensorFlow experiments on your own machine or server. It's for researchers and ML developers who need to understand training behavior, compare runs, and investigate model performance. It works entirely offline, including behind a corporate firewall or in a datacenter, so experiment data can stay within your own environment.

Latitude is a self-hosted AI agent monitoring platform for teams that need to find production failures and check that fixes work. It connects recurring problems to the sessions that caused them, then can dispatch Claude Code or Cursor with enough context to make a fix and open a pull request.

Distilabel is an open-source Python framework for engineers building datasets to train or evaluate AI models. It pairs synthetic data generation with LLM feedback, so a pipeline can create examples and judge their quality. It uses the Apache 2.0 license.

Obsidian Local GPT brings AI writing assistance into Obsidian, with local Ollama models for private, offline use or connections to OpenAI-compatible services. It's for people who want help with their notes while keeping control over where the AI runs. The plugin is open source under the MIT license.

New API is a self-hosted AI gateway for developers and teams that want several model providers behind one service. It builds on One API and converts between OpenAI Chat Completions, Responses, Anthropic Messages and Gemini formats, so apps and agents can switch providers without changing each client's connection settings.