Local & Self-Hosted AI Tools

ScribeDog is a Markdown editor for writers and note-takers who want AI help with documents they keep in their own folders. It shows formatted content while saving plain Markdown files that other editors can open.

Remembra Relay saves coding session handoffs so developers can switch assistants or resume a project on another machine without reconstructing its progress. The next agent receives a brief of completed work, unfinished tasks and failing checks.

wigolo gives AI agents web access from a server on your own machine. It's for developers who want coding assistants or self-hosted agents to gather web evidence and reuse what they've already fetched.

PowerInfer is a local LLM inference engine for developers and researchers running large models on a PC with a consumer GPU. Its performance gains depend on sparse models, which use only part of their network for each input.

ThunderAI is an AI email assistant for Thunderbird users who want help writing messages and managing their inbox. You can process email text with a local model or send it to a cloud provider.

LMMS Eval is a Python toolkit for researchers and model teams comparing AI models on text, image, video and audio tasks. It uses a shared evaluation pipeline to reduce differences caused by separate benchmark implementations.

NVIDIA NemoClaw is a self-hosted stack for people who want to run AI agents with controls over network access and credentials. It supports OpenClaw, Hermes and LangChain Deep Agents Code inside NVIDIA OpenShell sandboxes.

LibreChat is a self-hosted ChatGPT alternative for people and teams who want to use different AI providers in one chat workspace. It lets you switch models while keeping conversations in the same interface.

chatz is a self-hosted AI chat app that can display live charts, tables and status panels inside conversations. It's for individuals and teams who want to host their own chat interface, choose their model providers and connect tools. The app is open source under the MIT license.

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.

Agentlas OS is an open-source AI agent framework for projects that need specialist teams and shared project context. It runs on macOS, Windows and Linux, with local document indexing, semantic search and memory retrieval. You supply the model. Using a cloud model sends requests to that provider and may incur charges.

AgileRL is an open-source Python framework for teams training AI agents on their own tasks, including LLM agents and agents for robotics, finance or logistics. Its evolutionary hyperparameter tuning adjusts training settings during a run, reducing the need for separate tuning trials. The framework uses the Apache 2.0 license.

Ragas is a Python library for developers evaluating LLM applications and retrieval-augmented generation systems. Its non-LLM metrics compute text comparisons in your Python environment without a model, including string similarity, BLEU and ROUGE. Its model-based quickstart uses OpenAI's GPT-4o and an API key, sending evaluation inputs to OpenAI's cloud service. Local text scoring and cloud model judgments are separate evaluation options.

Step1X Edit edits existing images from written requests. It's for developers and researchers who want to run image editing on their own hardware, with control over the model and specialized training.

LightGBM is a decision-tree gradient boosting framework for classification, regression and ranking. It trains models on your own machine or across multiple machines, with GPU support for compatible configurations. The code is open source under the MIT license.

MCP Inspector is a developer tool for testing the Model Context Protocol servers that connect AI applications to tools and data. It lets you examine server behavior directly, without testing every interaction through an AI chat application.

x64dbg-MCP Server connects an MCP-compatible AI assistant to x64dbg for direct inspection and control of a debugging session. It's for reverse engineers, malware analysts and security researchers investigating Windows binaries.

TranscriptionSuite is a speech-to-text app for people recording lectures, transcribing conversations or dictating documents on their own hardware. Transcription works offline after the app and model downloads, keeping audio and transcripts local.

LocalAI is a self-hosted AI runtime for developers and teams that want to run models on their own hardware. It brings language, speech, vision and media generation into one server that existing AI applications can connect to.

ProofShot is a local browser verification CLI for developers reviewing UI work produced by AI coding agents. It saves browser interactions and errors as review artifacts so you can inspect what the agent tested.

Editable Design is an open-source toolkit of Codex skills for creating visual designs that remain editable. It covers posters, infographics and campaign artwork, with a separate skill for researchers who need PowerPoint diagrams from method descriptions.

Giskard Hub is an AI agent testing platform available hosted or on-premise for organizations that need testing within their own environment. Developers can also run its open-source Python library locally, but the library's LLM judges and attack generators require a model provider and API key, with integrations for OpenAI and Anthropic. Local execution doesn't make those evaluations offline.

Real-ESRGAN is a local AI upscaler for people enlarging images or restoring degraded images and video. It builds on ESRGAN, with dedicated models for general images, anime illustrations and animated video.

Reverse Skill gives AI coding agents workflows for reverse engineering, authorized penetration testing and CTF challenges. It's for security researchers who want their agent to select an analysis method and work with the tools available on their machine.

OpenClaw.NET is a self-hosted AI agent runtime for a personal assistant or a shared team gateway. It's an independent .NET implementation inspired by OpenClaw, with compatibility for supported parts of that ecosystem.

WeKnora is a self-hosted AI knowledge platform for teams that want to query documents, carry out tasks using them and organize them into a wiki. These functions share the same knowledge bases.

Kady is an AI research assistant for scientists who want to turn plain-language requests into analyses, literature reviews and research outputs. It works in a desktop workspace where you can inspect its code and files, redirect ongoing work or stop a run.

Astron Agent is an AI agent platform for teams building workflows that act across business systems. Its self-hosted edition combines workflow orchestration with tools that let agents carry out tasks.

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.

PersonalClaw is a self-hosted AI agent for one person who wants chat, ongoing tasks and personal knowledge in one web dashboard. It runs on Linux and macOS, with Docker support that also covers Windows. It's open source under MIT and is currently pre-1.0, with breaking changes expected. A one-time download supplies a tiny CPU model for offline chat without tools. Autonomous tool work needs your own Ollama model or a provider app.

Florence-2 is Microsoft's vision model for developers building applications that describe images, extract text or locate objects on their own hardware. One model handles several image tasks selected through text prompts.

Bisheng is a self-hosted AI application platform for teams working with business documents and processes. It supports tasks such as document review, support ticket assistance and fixed-layout report generation, including workflows that need human judgment during execution.

Distributed Llama runs language models across your own networked computers. It's for people who want to share inference work and model memory across several devices instead of fitting the whole workload on one machine.

Open Notebook is an alternative to Google's NotebookLM for researchers, students and professionals working with their own materials. It brings research and notes together while letting you choose what context an AI model can access.

ONLYOFFICE Docs is a self-hosted office suite for teams that want browser-based document editing and AI assistance on their own servers. It handles Word, Excel and PowerPoint formats (.docx, .xlsx and .pptx), alongside PDFs and fillable forms. The free community edition is open source under AGPL-3.0 and runs through Docker or on Linux and Windows servers.

CLODEx IDE is a desktop AI coding assistant for developers working on changes across multiple sessions. It keeps task history and workspace context across restarts, so you can return to unfinished work without rebuilding the task from chat messages.

Memmy Agent is a local memory hub for people who switch between AI assistants and want earlier decisions and project context available in the next conversation. It stores personal memory on your device by default. Direct agent tasks support your own credentials for a chosen model API. Model processing depends on the configured service or provider.

KADATH is a self-hosted AI agent runtime for developers and researchers comparing agents against a measurable goal. It runs successive generations of agents and selects stronger approaches, but model calls require OpenAI's cloud API, an API key and internet access.

Krita AI Diffusion adds AI image generation to the painting workspace for artists who want to refine artwork without leaving Krita. It lets you direct changes through selections and visual input.

ChatML is a desktop workspace for developers running several Claude Code tasks at once. It brings agent activity and code changes into one view so you can review work before merging it.

ai-jail is a sandbox for developers who want to limit the damage an AI coding agent can cause through mistaken commands. It targets accidental changes outside a project, and doesn't provide a security boundary against malware or hostile code.

SAHI is a Python computer vision library for developers detecting small objects in large images, including aerial imagery and surveillance footage. It divides images into smaller regions for detection, helping models find objects that occupy few pixels.

Agents Observe is a self-hosted dashboard for developers who want to inspect what Claude Code and Codex do during coding sessions. It helps you follow parallel agents and trace the commands or edits behind an unexpected result.

Stable Video Diffusion turns a still image into a short video clip for artwork, design and video generation research. Developers and researchers can run it on their own hardware, but text prompts can't direct the output.

Whisper Mate is a local-first transcription app for people who need text from recordings, calls or audio playing on their Mac. It brings transcription and subtitle work into one editor, with media processing that can stay on the Mac.

NVIDIA PhysicsNeMo is an open-source Python framework for engineers and researchers building AI models of physical systems. It combines physics constraints with simulation and observed data to train surrogate models that can predict behavior in near real time. The framework uses PyTorch and carries the Apache 2.0 license.