Local & Self-Hosted AI Tools

Transformer Engine is a library for developers building and running Transformer models on NVIDIA GPUs. It reduces compute and memory demands in training and inference through low-precision arithmetic and optimized model components.

OpenCLI lets AI agents and terminal users work with websites through their existing Chrome sessions. It's for people who want agents to interact with pages or repeat website tasks through reusable commands.

Codenotch is a desktop monitor for people who use AI coding assistants and local LLMs. A small display at a screen edge keeps usage readings and session states visible while you work in other apps.

Fish Diffusion is a Python framework for developers and researchers training diffusion models for text-to-speech, singing voice synthesis and singing voice conversion. It works with your own datasets and provides code you can adapt for different voice generation tasks.

Rivet is a desktop visual AI agent builder for developers working with connected prompts and application logic. Teams can inspect complex LLM workflows as graphs and run those graphs inside their own applications.

Agent Router is an open source AI gateway for teams connecting agents to model providers and MCP tools. It gives applications a shared entry point while platform teams manage access and routing.

Bifrost is an AI gateway for developers and teams building applications that use local LLMs or multiple cloud providers. It gives those applications a shared API for model access and a central place to manage usage.

Stable Diffusion XL is an image generation model for creators and developers who want to produce images on their own hardware or servers. You can start with a text prompt or use an existing image as input.

GPTeam is a self-hosted AI agent simulation for developers and researchers studying how agents communicate and work toward assigned goals. It runs locally in Python, while configured providers handle model calls through cloud APIs. The code uses the MIT license.

Needle is an AI model for developers building device assistants that turn requests into actions. It prioritizes automation over general chat, with smaller model variants for devices that have limited resources.

Frontman is an AI coding agent for designers, product managers and developers making small frontend fixes in an existing codebase. It connects visible elements in a running app to their source, so teammates can request changes without opening an IDE.

LocoAgent is an AI agent for automating social media work through logged-in Chrome sessions. It builds on a fork of the Claude Code CLI and runs on your computer, while social activity requires an internet connection and accounts on the relevant platforms.

gen.nvim brings LLM text generation into Neovim for developers and writers who want AI help within their editor. It can work with a selected passage or the current buffer, so you can ask about or revise the content you're editing.

nvtop is a terminal monitor for people checking GPU activity on local AI machines and compute servers. Its htop-style interface shows multiple GPUs and accelerators, including the processes using them.

Robby chatbot is an open source web app for people who want to ask questions about their documents, analyze tables in plain language, or summarize YouTube videos. You can run the Streamlit app on your own machine on macOS, Linux or Windows. A hosted Streamlit app is also available.

Playwright MCP gives AI agents browser control for testing and tasks that involve interacting with web pages. It reads structured accessibility snapshots, so agents can identify page elements without a vision model.

Max Headbox is a local AI agent for people who want a voice-controlled assistant that can carry out actions on a Raspberry Pi. It processes voice and runs models on your own hardware without relying on cloud AI providers.

exxperts is a local AI agent app for people who want ongoing work to carry across conversations while deciding what the assistant remembers. Persistent workspaces called rooms keep each agent's memory, files and tools together.

Moli is a headless browser for developers building AI agents, web scrapers and retrieval pipelines on their own machines or servers. It reads page content and executes JavaScript without continuously rendering a visual page.

Omit Redact is beta software for offline PII redaction on Windows 10 and 11, built for people preparing sensitive files to share in legal, healthcare, financial and public sector work. Local language models detect names, organisations and places in seven languages, alongside pattern checks for IDs and account numbers. Files and processing stay on your device, with no account, cloud service or telemetry.

MuseTalk is a local AI lip-sync model for video creators and developers building virtual avatars. It edits a face to match supplied speech, so you can dub existing footage or animate a portrait.

OrcaReplay is a local AI agent debugger for developers investigating failed coding runs or testing how another model handles the same task. It captures what happened beyond the chat transcript, including failed commands and changed files.

Diffusers is a Python library for developers and researchers building image, video and audio generation into applications or running models on their own hardware. It supports pretrained generation pipelines as well as custom diffusion systems.

ms-swift is a Python framework for developers and researchers training and deploying language and multimodal models on their own hardware. It covers model adaptation through evaluation and serving, with support for Qwen3, DeepSeek-R1, Llama4, Mistral, Qwen3-VL and InternVL3.5.

FastMCP is a Python framework for developers who want AI agents to use their applications and data through the Model Context Protocol (MCP). It covers both publishing tools and connecting to them, with support for servers that run locally or remotely.

aTrain is an offline transcription app for researchers and people working with recorded interviews. It turns speech into text on your own computer and can label segments by speaker. Recordings and transcripts stay local, so you can process sensitive material without uploading it to a transcription service.

Flash Linear Attention is a Python library for researchers and developers building language models on their own hardware. It supplies reusable components for exploring linear attention, sparse attention and state space architectures.

Fullmoon is a local LLM chat app for people who want conversations to stay on their Apple devices. It runs models on-device and works fully offline, with chat history saved locally.

OpenClaw is an AI assistant you run on your own computer for personal tasks or shared team use. It connects to existing messaging services, so you can reach the assistant through the apps you already use.

Meme Search is a self-hosted web app for finding images in your own meme collection by their content and text. AI-generated descriptions make the collection searchable without relying on filenames.

Mikupad is a browser-based LLM frontend for writers and anyone who wants to edit and guide generated text. It connects to a separate model backend and keeps writing context attached to your prompts.

Qwen-Agent is a Python framework for developers building assistants that use Qwen models to read files and carry out tasks with tools. It provides ready-made agent components and example applications for custom assistants and browser assistance.

ChatDev is a self-hosted AI agent platform for people building research, data analysis and software workflows. Its DevAll application runs the workflow backend on your computer or server, with a browser console for designing and overseeing agent teams. Model access uses your chosen provider's API credentials and endpoint; choosing a cloud provider sends model requests to that service.

GLiNER is a Python framework for extracting named entities from text using small models that run locally on CPUs and consumer hardware. It's for developers building document processing, personal data detection or search systems who need to choose their own entity types without training a model for each task.

DiffSynth-Studio is a diffusion model engine for developers and researchers generating media or training models on their own hardware. It combines inference and training, with memory-saving features for consumer GPUs.

Superior Trade Trading Terminal is for traders who want to turn a chart idea into an automated trade on Hyperliquid. You can sketch a price path or describe a strategy, then review the agent's proposed setup before deployment.

OpenFang runs recurring AI tasks on your own machine and reports their results to a desktop dashboard. It's for people who want research, monitoring or business automation to continue on a schedule without starting each job in chat.

ClearML is a self-hostable MLOps platform for researchers and engineering teams managing model development and production. It connects experiment records with datasets, training jobs and model deployment so teams can trace results back to the work that produced them.

NeMo Curator is an open source Python toolkit for ML engineers and data teams preparing AI training datasets. It provides repeatable curation pipelines that can run on a laptop or across a multi-node Ray cluster.

ripwire helps AI coding agents find the code they need and check the effects of their edits. It's for developers who want agents to work with focused repository context instead of reading whole files.

AutoGPT is an AI agent platform for teams automating recurring content, sales, research and operations work. Its hosted service centers on Experts coordinated by Otto; self-hosting provides the core workflow builder and agent runtime.

Pretype is a local AI writing assistant for people who want sentence suggestions across their Mac apps. It works in native apps, Electron apps and web text fields without separate plugins for each app.

Azure MCP Server gives AI assistants access to Azure services so developers can inspect and manage cloud resources through natural language requests. It brings Azure tools into the editor or agent they're already using.

VibeHQ Hub coordinates coding agents for developers who want several agents to work on the same project without conflicting interfaces or unfinished handoffs. It adds shared coordination to Claude Code, Codex and Gemini CLI while preserving each agent's native capabilities.

Newelle is a Linux desktop AI assistant for people who want to chat with local models and use AI to work with documents and files. It also supports external model providers.

FinRobot is an Apache 2.0 open-source equity research system for analysts and quantitative researchers. Its desktop app runs financial calculations locally and uses an LLM to interpret results and write reports. Built-in OpenAI and Anthropic connections send model requests to those providers; custom OpenAI-compatible connections can use a local vLLM backend. Research also needs external market data.