Local & Self-Hosted AI Tools

Tessera is a self-hosted literature review workspace for researchers who want to find papers, keep reading notes and compare findings in one browser interface.

ToolHive runs and manages Model Context Protocol (MCP) servers for developers and platform teams that want control over the tools their AI clients can access. It supports individual desktop use and shared deployments on your own infrastructure.

KServe serves LLMs and predictive machine learning models on your own Kubernetes infrastructure. It's for teams that need to put models from different frameworks into production through one serving platform.

Mastra is a TypeScript framework for developers building self-hosted AI agents and applications with local models through LM Studio. It supports gpt-oss, Qwen3 and DeepSeek through an OpenAI-compatible model server. The framework can also call OpenAI, Anthropic and Gemini, which send model requests to those remote providers.

DarkMoon runs autonomous penetration tests for security teams, DevSecOps engineers and red teamers. It discovers a target's technology stack, assigns specialist AI agents and tests vulnerabilities across connected systems.

Ellama is an AI assistant for Emacs users who want help with writing and code inside their editor. It handles requests about selected text as well as longer conversations and coding tasks that need several steps.

Smart Connections helps writers and researchers find earlier work related to their current Obsidian note. It surfaces relevant material without requiring a search query or links you've already made.

SoloMD is a Markdown editor for writers, researchers and developers who want plain text notes with AI assistance. It combines a Typora-style writing interface with tools for searching a note collection and letting agents work on it.

Wyoming Faster Whisper converts speech to text on your own hardware for Home Assistant and other Wyoming-compatible clients. It's for home voice systems that need local transcription and better recognition of household names.

EverOS is a Python library and memory runtime for developers building agents that need context across sessions and applications. It keeps conversations, files and task histories in readable Markdown that you can edit and version with Git.

Jean is a desktop and self-hosted workspace for developers running coding agents across multiple projects. Repositories, terminals and git operations run on your computer or server, while the connected agents use your own subscriptions or API access. With Claude Code’s standard cloud connection, prompts and model responses go to its remote provider.

gollama is a terminal app for people managing a local LLM collection in Ollama. Its keyboard-driven interface helps you compare downloaded models and clear out ones you don't need.

PipesHub connects company knowledge to AI search and agents for teams whose files and conversations sit across business apps. It can also supply that context to coding assistants and custom applications.

Leon is a personal AI assistant for people who want to automate tasks on their own computer or server. Its skills let you add actions suited to your needs.

M Flow is a self-hosted memory engine for developers whose AI agents need to recall past conversations and work preferences. It runs in Python or Docker and supports Ollama for local model use, alongside providers such as OpenAI and Anthropic. Choosing a cloud provider sends model requests to that service.

tiny-cuda-nn is a neural network framework for developers and researchers building small models, NeRF renderers and neural graphics applications. It handles training and inference on local NVIDIA GPUs.

PEFT is a library for developers adapting pretrained AI models on their own hardware. It trains a small portion of a model's parameters to reduce the compute and storage costs of full fine-tuning.

Memind gives AI agents long-term memory for projects, user preferences and past tasks. Developers can use it to carry context between sessions while keeping links to the material each memory came from.

PhotoPrism is a self-hosted photo and video organizer for people who want to browse, search and share a personal media collection on their own hardware or server.

QuPath is a free, open source desktop application for researchers analyzing whole slide pathology and microscopy images on their own computers. It combines image viewing and annotation with cell segmentation and interactive machine learning, so researchers can examine tissue and classify what they find within the same application. It runs on Windows, macOS and Linux.

FederatedScope is an open-source federated learning platform for researchers and teams building training systems across separate data holders. It can simulate clients and servers on one device or run them as separate distributed participants. Each participant loads its own data, while models can pass between participants through messages.

Topaz Photo is AI photo enhancement software for photographers correcting noise, soft focus and images that need enlarging for print. It suits wildlife, sports and event photography, where movement or poor lighting can leave a useful shot needing repair.

Audapolis is an editor for recordings where spoken words are the main material. Podcast producers, radio editors and people cutting interviews can work with a transcript through an interface similar to a word processor.

Shinkai lets people build AI agents to automate tasks without writing code. Its desktop app can run agents entirely offline with local models, including workflows that handle sensitive data.

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.

LocalText2Voice is an MIT-licensed desktop app for people producing audiobooks, lessons and podcasts from long texts. Its local speech engines work offline after model downloads, keeping your text and generated audio on your computer. It runs on Windows and Linux; macOS isn't officially supported.

LLM X is a browser chat interface for people running models on their own hardware. It brings multiple model servers into one place and lets you compare their responses within a conversation.

Composio's local CLI connects coding agents such as Claude Code to a hosted service for app actions and authentication. It's for people adding integrations to an assistant or building their own agents. The CLI runs on your machine, but requires a Composio account and internet access; model processing depends on the connected agent and its provider.

Lumina Note is a Markdown note-taking app for people who want AI help with writing and organizing a note collection. Its agent can work across the vault with your permission, while notes remain plain files you can edit and back up outside the app.

LiteRT-LM is Google's open-source framework for developers building apps that run language models on the user's device. It uses LiteRT for local inference across mobile devices, desktops and browsers, with GPU and NPU acceleration. The project uses the Apache 2.0 license.

biniou brings AI chat and media creation into one browser interface on your own computer or server. It's for people who want to work with several kinds of generative AI without switching between separate apps.

Letta is an AI agent platform whose App Server can run locally or on a self-hosted server. It's for people building assistants that retain context between conversations and use that memory in later interactions. Local agents can use Ollama or LM Studio with agent state and the model endpoint on your machine. Cloud model connections use remote providers.

Fragments is a Next.js template for developers building their own AI app generator, similar to Claude Artifacts or Vercel v0. It provides a starting point for an interface that generates and runs apps through chat.

PyOD is a Python library for detecting unusual records and behavior in data on your own machine or server. A shared fit/predict interface lets developers and data scientists compare classical and deep learning anomaly detectors without changing the surrounding application for each algorithm. Its code uses the BSD 2-Clause license.

Prompt flow is a Python toolkit for developers who want to run and evaluate LLM application workflows in their own development environment. Its chatbot examples call OpenAI or Azure OpenAI remotely using API credentials. Workflow execution and evaluation can run locally, while those model requests leave the machine.

fx is a coding agent for developers who prefer working in a terminal and researchers who want to embed an agent in their own software. Its shell-style interface keeps tool activity alongside the conversation and preserves terminal scrollback.

LLPlayer is a media player for language learners who study through video and audio. It pairs playback with tools for reading dialogue, checking unfamiliar words and revisiting scenes.

MindsDB Query Engine gives developers building AI agents one SQL interface for business data and document search. It runs as a standalone server and can also provide data access to MindsHub agents.

Docker MCP Gateway connects AI applications to tools and data through a shared gateway. It's for developers who want coding assistants to use the same server configuration while local tool servers run in isolated Docker containers.

Assistant is a self-hosted AI agent for people who want to delegate work by email and receive the results in their inbox. It uses a dedicated mailbox, separate from your personal email, and also accepts tasks through a browser workspace or dashboard. You control how much autonomy it has.

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.

Auto Browser lets AI agents operate a live browser that a human can take over when a login or fragile page needs attention. It's built for internal dashboards, account workflows and operator-assisted browser QA.

Olares is a self-hosted personal cloud OS for individuals and small teams that want AI agents, models and apps on hardware they own. It brings local AI and everyday file storage into a shared workspace you can access through a browser.

Windmill lets developers build internal apps, data pipelines and AI automation around ordinary scripts. Teams can share that code through browser interfaces and run it on infrastructure they control.

Dingo combines rule checks, LLM judges and agent-based evaluation to assess AI training data, fine-tuning datasets and production systems. It's an open-source Python tool under Apache 2.0 for data engineers, ML practitioners and researchers who need to find data problems and compare model or application quality. Evaluation can run locally or across a Spark cluster.

VoltAgent is a TypeScript AI agent framework for developers building assistants and automated workflows with local models through Ollama. Its VoltOps console can be self-hosted or used as a cloud service. Model execution depends on the provider: Ollama supports local inference, while OpenAI, Anthropic and Google connections send requests to those remote services.