Local & Self-Hosted AI Tools

Waves Clarity Vx is a proprietary AI audio plugin for removing background noise from recorded voices. It handles both speech and singing, so it's relevant to music producers working on vocal tracks as well as podcast creators and video editors cleaning up dialogue.

AnimateDiff generates animations with personalized Stable Diffusion models for artists and developers who want motion in their chosen visual style. Compatible image models don't need separate animation training.

Code Graph RAG helps developers understand and change unfamiliar repositories, including monorepos that mix languages. It maps code relationships into a knowledge graph so questions and edits can use context across files.

ALH Pro processes images, video and audio on your own computer. It's for people restoring older footage, enlarging photos or illustrations, and preparing media without uploading their files.

AgentSight is a local AI agent monitoring tool for developers investigating failed runs, slow steps or unexpected changes. It connects prompts and model calls to what agents actually do on the machine, including activity their own logs may miss.

MaxText is an LLM training library for researchers and engineers building models from scratch or adapting existing ones. It provides a reference implementation teams can modify for their own model designs, with training that scales from a single host to large clusters.

Klee is a native macOS AI chat app and agent for people who want an assistant to work with files on their Mac. It runs models locally through MLX, and downloaded models can chat offline without an account or API key.

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.

APPFL is an MIT-licensed Python framework for researchers and data scientists who want to train machine learning models across distributed clients while keeping training data decentralized. It supports user-defined models and lets teams test privacy-preserving federated learning methods in simulations or real distributed experiments.

Kestra coordinates AI, data and infrastructure workflows for teams that need to connect tasks and track their execution. It can run existing scripts and containers, so workflows can span tools written in different languages.

KanDev is a self-hosted workspace for developers managing AI coding tasks and reviewing the resulting changes. It organizes work on kanban boards and lets you define workflows with your own agent choices and review gates.

torchtitan is a training platform for researchers and developers experimenting with generative AI models on their own GPU servers or clusters. Its replaceable components and extension points support work on model architectures and training infrastructure.

IndicF5 is a text-to-speech model for developers and researchers who need to generate spoken audio in Indian languages. It supports Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil and Telugu.

Understory gives AI agents persistent knowledge across sessions in Markdown files you can read, edit, and track in Git. It's for people who want their agents' memory accessible outside a chat history.

BoTorch is a Python library for researchers and experienced AI practitioners who build Bayesian optimization algorithms. It helps choose which inputs to evaluate next by fitting a probabilistic model to observed results. Its main appeal is control over the models and decision rules used in that search.

TrailSnap is a self-hosted AI photo album for people and families who want to organize their pictures and retrace past trips. It connects photos with places and travel records so you can find a particular memory or review a whole journey.

CubeSandbox is a self-hosted sandbox service for teams that need AI agents to execute code on their own infrastructure. Each sandbox has its own operating system kernel inside a hardware-isolated MicroVM.

Morphic is an AI search engine for people who want answers they can check against web sources. It searches the web and reads URLs to gather information for a question.

RealChar lets you create AI companions with their own personalities and hold live voice or text conversations. It's for people who want to shape a character and host the app themselves while using external AI services for replies.

Nanotron is a Python library for researchers and developers training language models on their own datasets and GPU infrastructure. It supports training on one machine or across multiple servers.

Optimum Quanto is an open-source PyTorch library for developers who want to reduce the memory needed to run models on their own hardware. It handles language models and image-generation models, with integrations for Hugging Face Transformers and Diffusers. The project is in maintenance mode, accepting minor fixes and documentation work rather than major features.

Lemon AI is a local AI agent for people who want to research topics, write code and analyze data on their own hardware. It also lets you revise generated HTML reports and pages without asking the agent to recreate the whole result.

GROBID turns scientific and technical PDFs into structured TEI XML on your own machine or server. It's for researchers and developers who need article metadata, full text and bibliographical references for search, analysis or document collections. The software is open source under Apache 2.0.

Excire Search is a Lightroom Classic plugin for photographers who need to find material in large catalogs and choose between similar shots. Its AI analyzes photos and video clips locally without transferring them to a cloud service.

Jsonformer is a Python library for developers who need structured JSON from language models running through Hugging Face Transformers. It controls the JSON structure while the model supplies the values, reducing reliance on prompts that ask a model to produce correctly formatted output.

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.

Jupyter AI is an extension you run with your own JupyterLab server, giving agents access to notebooks, files and terminal commands in that environment. Model access comes from your separately installed agent; Claude Code’s standard connection, for example, sends prompts to its cloud provider. Its built-in Jupyter MCP server connects agents to notebook operations, alongside file editing and terminal commands. Chat sits beside the work.

Orbi is a self-hosted AI coding agent for developers and teams who want GitHub backlog tasks carried through to reviewed pull requests and tagged releases. It runs on Linux or macOS, on your own computer or server. The macOS launchd scheduler is documented but has not yet been verified on real hardware. The open source core is free under AGPL-3.0.

BitNet is Microsoft's local LLM inference framework for developers and researchers working with compatible 1-bit models. Its bitnet.cpp runtime focuses on faster inference and lower energy use on your own hardware.

Joplin Jarvis is an AI assistant for people who keep their research and writing in Joplin. It uses your notes as context for conversations and helps you find related material or annotate your collection.

Ollama runs open models for people who want local AI applications, model chat or a backend for coding assistants. It provides a command-line interface and an API, with a choice between inference on your hardware and its cloud service.

Noted is a desktop notebook for people who want connected notes and AI help while keeping their writing in ordinary Markdown files. Notes live in a folder on your machine, where other editors and backup tools can use them.

MacWhisper turns recordings into editable transcripts for people working with interviews, lectures, podcasts and meetings. Local transcription works offline and keeps the audio on your Mac.

Octogent is a local web dashboard for developers coordinating several Claude Code sessions on one codebase. Its UI and API run on your machine, where it stores job context and transcripts. The supported workflow requires Claude Code. With its standard cloud connection, prompts and model outputs go to a remote provider; Octogent hosts the dashboard and task coordination.

OpenChatCut is an AI video editor for creators who want to direct edits through conversation and refine them manually. Agent changes become editable clips, captions, effects and audio tracks, so you can inspect or undo them in the same project.

HilbertRaum is a local AI workspace for people working with confidential documents, research, or personal archives. It lets you use AI without sending your files or conversations to an external service.

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.

FlagEmbedding is a Python toolkit for developers building semantic search and retrieval-augmented generation (RAG). It runs embedding models to find relevant text and rerankers to refine the order of retrieved results.

Nanobrowser is a browser AI agent for people who want to delegate repetitive web tasks and research. It carries out actions inside the browser while letting you choose the models that handle the work.

AI Review is an AI code review tool for development teams that want automated feedback inside pull and merge requests. It runs in your CI/CD environment and uses your chosen LLM to review code against your team's guidelines.

Visions of Chaos combines generative AI tools with fractals and complex-system simulations in one application. It's for digital artists, educators and people who want to explore machine learning or mathematical patterns without working through the equations themselves. Its AI models run privately on your own hardware, without paid online APIs or backend usage logging and telemetry.

funes gives coding agents a searchable memory of past work. It's for developers who want earlier decisions, reasoning and findings to remain available when they start another session or switch agents.

HuggingChat UI is a browser-based ChatGPT alternative for people and teams who want to host their own chat service. It's the application behind Hugging Face's hosted HuggingChat, and it connects to a separate model backend.

Orpheus TTS generates speech for developers building voice applications or creating custom voices. Its Llama-based models support local inference and let you control how spoken text sounds.

Meilisearch is a search engine for developers adding search and AI retrieval to websites, apps, catalogs or internal data. You can host the engine on your own server or use the separate managed Meilisearch Cloud service.

Skales is an AI agent for people who want help with files, browsing, email and coding on their own devices. It can keep working on a goal after you close the chat and resume unfinished goals after a restart.