Local & Self-Hosted AI Tools

Gauntlet Loop is an AI agent skill for people who want generated websites, writing or software judged against a specific example. It writes a prompt that asks an agent to build, compare and revise work against a reference you choose.

FAISS is a vector search and clustering library for developers building applications that compare embeddings or other vector data. It runs on your own machine or server and lets you balance search accuracy against speed and memory use.

AgentRQ lets people assign work to AI agents, follow their progress and answer requests for decisions from a browser, phone or desktop app. Agents run on computers you own; the task dashboard can run on your server or the hosted service.

OpenBrowser is a self-hosted browser automation agent for people who need visual judgment and interaction across web pages. Its server and Chrome extension run locally, but the documented Qwen setup sends model requests to DashScope's cloud API and requires an API key and internet access. Browser execution stays local; model processing uses the remote provider.

Excel AI Assistant is an MIT-licensed add-in for people who want AI to make changes directly in their spreadsheets. It runs on your machine alongside Excel for Mac, Windows or the web, and uses plain-language requests to edit the open workbook.

XTTS v2 generates speech from text on your own hardware, using a voice recording as a reference. It's for developers adding speech to applications and researchers adapting a speech model to their own data.

Roboflow Inference runs computer vision models on images and camera feeds for teams building inspection, monitoring and image analysis systems. You can host it on your own computer, server or edge device.

Ringer coordinates parallel AI coding agents on your machine. It's for developers who want to divide implementation work among workers and judge the results with executable checks.

Lethe is a local document de-identification app for people who work with confidential contracts, client records or deal documents and want to use AI without sharing the names involved. It replaces names with consistent placeholders, then restores them in AI-generated replies, including summaries and translations.

gpt-oss is a pair of OpenAI reasoning models for developers who want to run a local LLM or serve models on their own hardware. The smaller model targets local and specialized applications; the larger one targets general-purpose tasks that need more reasoning.

TUUI is a desktop AI chat application and Model Context Protocol (MCP) client for people who want to use model-connected tools in one interface. Developers can also extend it to build their own desktop AI applications.

LocalScribe records online meetings and turns them into timestamped transcripts on your PC. It's for people who need private meeting records they can review and correct while retaining the original text and audio.

KaaS is a self-hosted AI knowledge base for personal research and teams preserving knowledge across role changes. It turns notes, documents and transcripts into wiki articles you can read, edit and query.

Stanza is a Python NLP library for developers and researchers who need to analyze text in multiple human languages on their own hardware. It turns raw text into linguistic annotations, such as word forms, grammatical relationships, and named entities. It's open source under Apache 2.0.

UGTLive translates text on your Windows screen for games, manga reading and language study. It places translations over the app you're viewing and requires an NVIDIA RTX 20, 30, 40 or 50 series GPU with at least 8 GB VRAM.

RAGFlow helps teams build AI agents that answer questions using their own documents. It extracts content from complex files and retrieves supporting material that readers can check.

PDF Editor Offline helps people edit and prepare sensitive documents on their own computer. It works offline without an account, and desktop and source modes process documents on the device without uploads or document telemetry.

Skyvern automates browser tasks for teams handling forms, vendor portals and repeated data collection. It uses vision models to identify page elements, helping workflows adapt when website layouts change.

Chandra OCR converts document images and PDFs into text that retains page structure. It's for people processing scans, handwritten records or documents whose tables and forms need to survive extraction.

Activepieces is a self-hosted automation platform for teams that want AI agents and app workflows on their own servers. It runs with Docker or Kubernetes, alongside a managed cloud offering. Self-hosting controls where the app runs; connections to Anthropic, OpenAI, AWS Bedrock or Google Gemini still send model requests to those providers using your credentials.

NLM Memory collects coding conversations into one searchable store on your machine. It's for developers who switch agents or editors and need earlier reasoning to remain available when decisions change.

Aperty is a desktop AI portrait editor for photographers working on weddings, family sessions and other portrait shoots. It helps apply consistent retouching across a photo set while leaving control over the strength of each adjustment.

StyleTTS 2 is a text-to-speech model for developers and speech researchers who want to generate expressive speech on their own hardware. It can choose a speaking style from the text without a reference recording.

CodeFormer restores degraded faces in photos and videos for people working with damaged images and researchers developing face restoration tools. Its quality control lets you balance a cleaner result against fidelity to the input face.

bb-browser gives AI agents access to your local Chrome session, including the website accounts you're already signed into. It's for people building agents that need to work with authenticated websites without a separate API integration for each service.

Text Generator is an AI writing assistant for Obsidian users who want to turn material in their notes into drafts, summaries and ideas without leaving their knowledge workspace.

NVIDIA Object Oriented Agents (NOOA) is a Python framework for developers building AI agents in their own projects. It supports local models through Ollama and vLLM via LiteLLM, with Qwen3 examples for both backends. It also supports Anthropic and OpenAI models, which send requests to those remote providers.

Unstructured is a document processing library for developers preparing files for LLM applications. It turns text documents and images into structured output that applications can work with.

Unsloth is a desktop app for people who want to chat with models, train them on their own data, and create media on their own hardware. Its no-code interface brings these tasks into one workspace.

CodeFuse ChatBot is a self-hosted AI assistant for developers and DevOps teams who want answers grounded in their own code repositories and documentation. It combines repository analysis with agents that can use tools and execute code in a sandbox, covering work across design, coding, testing, deployment and operations.

SpecShip is a workflow extension for Kiro that coordinates AI agents through planning, implementation, review and pull request preparation. It's for developers who want agent work checked against written requirements and tests.

Inbox Zero helps people with busy inboxes sort incoming mail and prepare replies. It works alongside your existing email client and supports Gmail, Google Workspace and Microsoft Outlook.

MemOS gives AI agents persistent memory across conversations and tasks. Developers can use it for assistants that recall preferences, support history or earlier work, with on-device, self-hosted and hosted storage options.

AI Toolkit (ostris) is a training suite for people fine-tuning image and video generation models on their own hardware or rented servers. It provides a browser interface and command-line access to training jobs.

DeepGEMM is an open-source CUDA kernel library for developers building LLM training and inference systems on their own NVIDIA GPUs. It supplies matrix operations and specialized computations for mixture-of-experts (MoE) models.

MemSearch gives coding assistants searchable project history across sessions. It's for developers who want to recover earlier fixes, revisit design decisions or continue work in another agent.

Browser Use is an AI browser agent for developers automating tasks across websites. It can work through pages and forms to complete jobs such as booking an appointment.

OpenAgent is a personal AI assistant for people and teams who want agents to work with their documents and carry out tasks on their own computer or server.

smart:deess is a proprietary AI audio plugin for producers, mixers and speech editors who need to control harsh consonants and plosives in voice recordings. It runs in a DAW on macOS or Windows and combines detection of individual speech sounds with spectral processing to adjust their tone as well as their level.

AWS MCP Servers connects coding assistants and AI agents to AWS documentation, infrastructure tools, and cloud services. It's for developers who want their assistant to work with AWS resources and service-specific guidance.

XAgent is an experimental self-hosted AI agent for multi-step coding, research and data-analysis tasks. It plans subtasks, revises plans as work progresses and dispatches actions to agents. A command-line interface and browser UI let you guide a run or provide missing information.

Raycast Ollama is a desktop launcher extension for people who want to chat with models and work on text without leaving Raycast. It connects to Ollama running on your machine or a remote server you choose.

JamAI Base is an AI backend for developers building chatbots and applications that use their own documents and structured data. Its spreadsheet-like interface brings prompts, generated data and LLM workflows into tables.

Home-LLM connects Home Assistant to language models for voice and chat control of smart devices. It's for Home Assistant users who want those requests handled on their own hardware.

diffusion-pipe trains image and video diffusion models on your own GPU hardware. It's for people fine-tuning models that are too large to fit on a single GPU or who want to distribute training across several GPUs.

MindFS is a self-hosted browser gateway to AI agents and project files on your workstation, for people who want to continue coding from another computer or phone. It requires an installed agent CLI and includes no AI model. With Claude Code's standard cloud connection, execution happens on your host while prompts and model context go to its remote provider. The installed agent handles model access; MindFS hosts browser access to its work.