Local & Self-Hosted AI Tools

FastDeploy is a self-hosted inference toolkit for teams deploying language and vision-language models on Linux servers. Built on PaddlePaddle, it supports offline inference and online serving.

Scriberr transcribes recordings locally for people who want to review meetings and voice notes without uploading audio to a cloud service. It combines transcription with playback, annotations and optional questions about the recorded conversation.

QuickDesk is a remote desktop app that lets AI agents operate other computers through a built-in MCP server. Developers and administrators can automate desktop tasks while watching the agent's actions and intervening when needed.

Presenton is an AI presentation maker for teams turning reports and source documents into decks, and developers adding slide generation to their apps. It can reuse an existing PowerPoint design so generated presentations follow your own layouts.

LLM Wiki is a desktop AI knowledge base for people building a research library or personal reference collection. It creates lasting, linked pages from your documents and updates them as your sources change.

IndexTTS is a local text-to-speech system for people creating spoken audio and developers adding speech generation to applications. It can reproduce a voice from a single reference recording.

BrowserWing is a local browser automation tool for developers and AI agent users who need repeatable website tasks and structured data. It lets you record a workflow once and make it available to agents as a reusable action.

LobsterAI is a desktop AI agent built on OpenClaw for office work and local projects. It operates tools on your computer and keeps sessions, configuration and memory there. You select each agent’s model separately from its workspace and tools.

Ludwig is a framework for developers and researchers training custom AI models without writing their own training loops. It handles preprocessing, training and evaluation from a model definition, covering LLMs as well as tabular and multimodal tasks.

SearchBox searches inside documents for people who remember a topic or phrase but can't find the file it came from. It keeps existing folders in place and makes their contents searchable.

SpecForge is an open-source framework for teams training draft models to speed up LLM inference in SGLang. It suits developers who want to train on their own hardware and use the resulting drafts directly with SGLang serving.

Harbor helps people experiment with local LLMs by connecting model backends, chat interfaces and supporting services. Its CLI and companion app manage those connections in a shared development environment.

Best Claude HUD keeps session and repository information visible for developers working in Claude Code's terminal interface. It helps you check the active model, available context and working tree without leaving the conversation.

LocalVocal turns speech into live captions inside OBS for streamers and people recording video. It processes speech on your computer, so transcription can work offline without sending audio to a cloud service.

JARVIS RD Assistant is an open source, self-hosted workspace for researchers who want to search scientific literature and trace AI-generated answers back to papers. It runs on your own hardware with Ollama and connects literature review with PDF annotation, learning cards and research projects. It uses the Apache 2.0 license.

Page Assist is a browser extension for people who run AI models locally and want to use them while browsing. It lets you ask questions about a page without leaving it or open a separate tab for longer conversations.

Curator is a Python library for developers building LLM training datasets or extracting structured records from existing data. It supports pipelines that generate data in stages and process many model requests.

Pico MLX Server is a macOS app for people who want to run MLX models locally and use them with an existing AI chat client. It gives MLX Server a graphical interface and exposes local models through an OpenAI-compatible API. The project is open source under the MIT license and requires macOS Sonoma or later.

Hyperopt is a Python library for developers and researchers who need to tune model hyperparameters across complex search spaces. It can handle continuous values, discrete choices and conditional parameters, such as settings that apply only when a particular model or approach is selected. It runs within your Python project, with support for both serial and parallel optimization.

FastEmbed is a Python library for developers building semantic search and retrieval-augmented generation (RAG). It turns text into vectors and evaluates search results on your own hardware without requiring a cloud embedding API.

Accelerate is a Python library for developers and researchers who write their own PyTorch training loops. It handles hardware and distributed execution so they can keep control of how their models train.

NVIDIA FLARE is a Python SDK for researchers and data scientists who want to train models across participating sites while keeping training data local. Platform developers can also use it to build systems for collaboration between organizations. It supports on-premise and cloud deployments and is open source under the Apache 2.0 license.

GPTLocalhost connects Microsoft Word with language models for people who want to use AI while working in Word. You can choose a local model or a cloud model.

Latitude is an AI agent monitoring platform for teams investigating production failures. It links recurring problems to the conversations and tool calls behind them, then gives coding agents the context to work on a fix.

Contrabass coordinates AI coding agents working through project issues, for developers managing several tasks or agent teams. It runs locally on macOS and Linux and reimplements OpenAI's Symphony approach.

Albert coordinates Claude Code agents for developers who want to hand off a coding goal that spans several tasks. It plans the work and continues through successive rounds until it reaches the goal or a requested review checkpoint.

ZettaBrain RAG is a self-hosted document assistant for individuals and small teams working with policies, contracts and internal manuals. It helps them find answers and draft documents from files they already keep on their own infrastructure.

Hermes Browser Extension puts an existing Hermes Agent in a browser side panel for people who want to ask about the pages they're reading. Page context works through local or remote API connections; Hermes Cloud and dashboard-ticket connections are chat-only.

Real-CUGAN NCNN Vulkan is a command-line AI image upscaler for people enlarging anime artwork on their own computer. It uses Real-CUGAN models through the ncnn runtime to increase image resolution and reduce noise.

AI Copywriter is a portable agent skill for people writing marketing copy and product interface text. It builds on blader's Humanizer, pairing copywriting guidance with rules for removing formulaic AI phrasing.

Nanocoder is a terminal AI coding assistant for developers who want to choose which model works on their code. It can use local models through Ollama or send requests to a hosted provider through an OpenAI-compatible API.

Agency Orchestrator coordinates specialist AI roles for developers and solo builders working on product plans, research or content. A task description can become a team that divides the work and combines its results.

Fable Orchestrator is a local routing skill for developers who want separate planning and implementation roles in Codex. Claude Fable makes planning decisions and reviews results, while Codex retains control of the workspace and tools.

MOSS TTS generates speech for developers and creators working on narration, dubbing and other long audio content. It supports consistent voices across long passages and can clone a speaker from reference audio without separate training for that voice.

Ultimate Vocal Remover separates vocals and other parts of songs on your computer. It's for people preparing karaoke tracks or isolating audio for music projects.

Claude Code Agent Monitor gives developers one place to follow coding agents and inspect their work across Claude Code, Cursor and Codex. It keeps conversations and activity available for review after a session ends.

Seldon Core is an AI model serving framework for teams running machine learning models and LLM applications on Kubernetes. It manages individual models and applications with multiple processing stages.

Claw Orchestrator gives developers one interface for multiple coding agents and checks their results independently. You define acceptance criteria, and the runtime executes the checks and keeps the evidence on disk.

search2ai is a self-hosted search gateway for developers adding web access to AI agents and chat clients. It connects your chosen search services through one interface, with backup providers when requests fail.

OpenVINO Model Server is a self-hosted inference server for developers and teams serving AI models on their own machines or servers. It uses OpenVINO to run workloads on x86 CPUs, including Xeon, with acceleration for Intel integrated and discrete GPUs and NPUs. It's open source under Apache 2.0.

Maid is an Android AI chat app for people who want to chat with models on their phone and access remote models from the same interface. Local conversations work without an internet connection.

FastChat is a self-hosted LLM platform for developers and researchers who want to serve chat models on their own hardware and compare their responses. It powers Chatbot Arena and includes a locally hosted side-by-side comparison interface. The Python code is open source under Apache 2.0; model licenses apply separately, including Llama's license for Vicuna.

sonible smart:comp is a proprietary audio compressor plug-in for producers, mix engineers and sound designers working on macOS or Windows. It analyzes your audio and maps suitable compression settings in a visual Compression Matrix, so you can compare compression characters while keeping access to conventional controls.

SwarmUI is a self-hosted AI image generation interface for people who want both straightforward generation controls and access to detailed ComfyUI workflows. You can use it with models running on your own hardware.

total-agent-memory gives AI coding agents persistent memory of decisions, fixes and project conventions across sessions and repositories. It's for developers who don't want to keep explaining earlier work to Claude Code, Codex CLI, Cursor or another MCP client.

Ollama GUI is a browser interface for people who want to chat with models running through Ollama on their own hardware. It brings conversation editing, attachments and model management into one chat app.