Local & Self-Hosted AI Tools

DeepCell is an open-source Python library for researchers analyzing individual cells in biological images. It runs locally and uses TensorFlow to identify whole cells or nuclei and track cells through time-lapse movies. Its Apache 2.0 license allows users to adapt the library for their own research.

GenOffice is a Microsoft Office alternative for people who want to edit documents on their own computer and let an AI agent make changes inside the files. It works with native .docx, .xlsx and .pptx files alongside PDF, Markdown and HTML.

Dify is a visual builder for teams creating AI agents and applications that use their own data and tools. Its canvas makes application logic visible so teams can inspect and test how a task proceeds.

nvitop is a terminal GPU monitor for people running AI workloads on NVIDIA hardware. It shows GPU activity alongside the processes using it, so you can check resource use and investigate busy devices.

Substra is open-source federated learning software for teams that need to train and validate machine learning models across distributed datasets. It supports production use across a network, as well as simulations on a single machine for testing and debugging federated learning code.

sage-wiki turns a document collection into a linked wiki and knowledge graph for researchers, teams, and AI agents that need reusable knowledge across tasks.

Bergamot Translator is a local AI translation library for developers building translation into browser or native applications. People who want to translate web content can use it through the separate TranslateLocally extension for Firefox.

Notion Knowledge Assistant is a self-hosted Telegram bot for people who keep research, reference notes or study material in Notion. You run the Python app on your own hardware or server, including through Docker, but answers depend on OpenAI's paid cloud API. It also needs connections to Notion and Telegram, so self-hosting doesn't make it an offline assistant.

Fairlearn is an open-source Python toolkit for data scientists who need to examine how machine learning models affect different groups of people. It combines fairness assessment metrics with algorithms for reducing observed disparities, under the MIT license.

AVCLabs PhotoPro AI is a paid desktop AI photo editor for Windows and macOS that uses your computer's hardware for image processing, with GPU acceleration available. It combines restoration and enhancement with text-prompt edits for photographers, product sellers and people repairing old family photos.

QAnything is a local knowledge base for people and teams who want to ask questions about their own documents. It supports offline operation and questions across Chinese and English document collections.

Adrian is a runtime security tool for teams whose AI agents can use tools or act on external systems. It checks planned actions against the agent's intended task and can intervene before an unsafe action runs.

Molmo is Ai2's family of vision-language models for working with images and text on your own hardware. It's aimed at developers and researchers who want to train models or evaluate them on visual tasks.

ExtractThinker is a Python library for developers who want to extract structured data from documents using models running locally through Ollama. It also supports OpenAI, Anthropic and Groq. With a cloud provider, extraction sends document content to that service, requires provider credentials and may incur charges.

Trainable Weka Segmentation is a local image segmentation plugin and Java library for Fiji. It's for researchers and image analysts who want to teach a classifier which image regions belong to each class, then apply that model to other images or stacks. It's free and open source under GPL-3.0.

SearXNG is a self-hosted metasearch engine for people who want to combine search services without user tracking or profiling. It's a fork of searx, and web searches require internet access because external services supply the results.

Open Science Desktop brings research agents, notebooks and project files into one workbench for researchers who want to inspect the work behind an AI-generated result. Agents can carry a research topic through literature review, experiments, analysis and manuscript writing.

MFLUX is a Python toolkit for creators and developers who want to generate and edit images on an Apple Silicon Mac. It provides a command-line interface for working with models locally.

agentacct is a local dashboard for developers who want to see what coding agents did across projects and compare their work with resource use. It brings recorded activity and results into task receipts rather than relying on an agent's claim that a job is finished.

ClawLess is a browser app and SDK for developers who want AI agents to write and execute code in an isolated workspace. Execution runs in your browser without a backend server, but model requests go to Anthropic, OpenAI or Google through API keys, so AI tasks need online services.

SkyPilot manages AI training, inference and development workloads across infrastructure you control. It's for AI teams sharing compute and infrastructure teams managing jobs across clusters and cloud providers.

OpenCodeReview is a locally installed AI code review CLI for developers who want findings tied to specific code lines. It sends code to a configured LLM endpoint through OpenAI- or Anthropic-compatible APIs. The local CLI handles the review process; model inference depends on that endpoint.

EvalScope is a Python evaluation framework for teams comparing AI models or assessing a model service before deployment. It connects scores to the prompts, predictions and reviews behind them so you can examine individual results.

Supervision is a Python library for developers building applications around computer vision models. It supplies tools for working with predictions and datasets, so you don't have to build those parts of an application yourself.

mcp-use is a TypeScript framework for developers building MCP servers and apps for ChatGPT, Claude, and AI agents. It brings tool definitions, interactive interfaces, and testing into one development framework.

PocketPaw is a self-hosted AI agent for people who want an assistant to write code, manage files and act on websites from their own computer or server.

LanceDB is a vector database for developers building AI retrieval applications and teams working with multimodal datasets. Its embedded library can run locally or in your own cloud.

rclip searches folders by what their images contain, without requiring tags or a separate photo library. It's for people who keep image collections on their own computers or servers and want to search them from a terminal.

OKF Agent Memory gives AI coding agents persistent project knowledge across sessions. It's for developers who want agents to retain architectural decisions and project constraints without loading the entire knowledge base into every prompt.

E2B provides isolated execution environments for developers building coding assistants, computer-use agents and background jobs. You supply the model and agent logic; it supplies the machine where the agent works.

LivePortrait animates a portrait with facial expressions and head movements taken from a driving video. It's for creators who want to animate still faces or edit portrait videos on their own hardware.

Infinity Embeddings is a self-hosted model server for developers building semantic search and retrieval-augmented generation applications. It runs retrieval models on your own hardware and can serve several models together.

Sesame CSM is a speech generation model for developers and researchers building voice applications on their own hardware. It generates spoken output from text and audio inputs, including earlier parts of a conversation.

PixlStash is an image manager for photographers culling shoots, creators reviewing AI images and people preparing datasets. It helps you find relevant pictures and review which ones to keep in large collections.

llamafile packages a language model and its runtime in a single executable for people who want to run models locally or share a ready-to-run model with others. Recipients don't need to install a separate runtime.

SimpleTuner is a diffusion model training toolkit for creators and researchers adapting image, video or audio models to their own datasets. Its web dashboard also supports teams sharing GPU workers.

Marqo Open Source is a self-hosted search engine for developers building document search, product discovery, or retrieval for AI applications. The project is deprecated and no longer receives updates.

Portkey Gateway routes application requests across model providers through an OpenAI-compatible API. It's for developers who need shared routing and failure controls when working with multiple AI backends.

projectmem gives AI coding assistants a persistent record of a project's debugging history and architectural decisions. It's for developers who want agents to carry useful context between sessions and check past failures before repeating them.

BoTorch is a Python library for researchers and experienced AI practitioners who build Bayesian optimization algorithms. It helps choose which inputs to evaluate next by fitting a probabilistic model to observed results. Its main appeal is control over the models and decision rules used in that search.

Zed is a desktop code editor for developers who want coding assistance from models running on their own machine or infrastructure they control. Its Agent and Inline Assistant can use Ollama, llama.cpp, LM Studio or a local OpenAI-compatible server. The editor connects to these model servers, which perform inference.

llmware is a Python framework for developers building applications that answer questions using their own documents or carry out multi-step AI agent workflows. It focuses on small, specialized models that can run on laptops, edge devices, and self-hosted servers.

PageIndex is a document retrieval engine for developers building question answering over long PDFs, including financial reports, legal documents and technical manuals. It uses an LLM to select relevant sections from a document tree without a vector database or document chunking.

Weft is a language and framework for developers who want to run AI workflow orchestration on their own machine. Its runtime requires Docker, and its graph editor works in VS Code and compatible forks. Self-hosting the workflow doesn't make its model calls local: the included WhatsApp support bot uses OpenRouter for inference.

Silero Models is a collection of pretrained text-to-speech models for developers adding voice output to applications or services. It suits projects that need speech generation on their own hardware, including support for Turkic and Caucasian languages.

Cezar manages AI coding agents on your computer or your own server. It's for developers coordinating work across repositories who want to review tasks, agent activity and code changes in one browser interface.