Local & Self-Hosted AI Tools

SGLang is a self-hosted inference framework for teams serving AI models to applications. It supports production workloads on a single GPU or across distributed clusters, including AI agents and reinforcement learning rollouts.

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.

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.

ChatOllama is an AI agent app with a command-line interface for people who want to use local models or hosted services from the same client. It discovers available models from connected providers, including installed models at an Ollama endpoint.

Open Multi Agent is a TypeScript framework for developers building self-hosted AI agent teams. It lets you coordinate work across agents, require human decisions before consequential actions, and inspect what happened afterward.

VoiceCraft generates speech from text and edits existing recordings using a few seconds of a speaker's voice as reference. It's for researchers and developers who want to work with voice generation on their own hardware without training a separate model for each speaker.

scikit-learn is a Python machine learning library for people building predictive models and analyzing data. It combines algorithms with data preparation and evaluation tools so you can compare approaches within one library.

text-generation-webui, also called TextGen, runs language models on your own hardware for chat, writing and application integrations. You can use it as a desktop app or a self-hosted browser interface.

10xProductivity extends a coding agent into a personal assistant for work that spans messages, tickets and documents. It's aimed at people working within company restrictions on new automation platforms, using the accounts and permissions they already have.

OpenScribe is an AI medical scribe for clinicians who want to turn recorded patient encounters into structured draft notes. Its desktop workflow builds on StenoAI and keeps transcription and note generation local. It's not HIPAA compliant, and every generated note requires clinical review.

Bitterbot is a personal AI agent for people who want an assistant that remembers ongoing work across conversations. It runs on your own machine and can keep working between conversations while the machine is on.

Docker MCP Gateway connects AI applications to tools and data through a shared gateway. It's for developers who want coding assistants to use the same server configuration while local tool servers run in isolated Docker containers.

Memorix keeps project memory for AI coding agents across chats and switches between tools. It's for developers who want decisions, fixes and unfinished work to remain available to the next session.

NullHub is a self-hosted management console for people running NullClaw and its supporting tools. It brings agent instances, workflow runs and task queues into one browser dashboard.

RSI Harness builds on the Pi coding agent for developers and researchers who want to version and share tailored agent setups. It collects each setup into a local directory bundle called a Genome.

SmartSub helps video creators subtitle recordings and dub them into other languages. You can use its transcription, translation, proofreading, dubbing and export tools separately or combine them for batch processing.

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.

OLMo Core is a Python library for researchers and developers building and training OLMo language models. Its PyTorch components and official training scripts suit teams working with model training code on their own hardware or servers.

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.

LlamaCoder is a self-hostable AI app generator for people who want to turn a written idea into a small app with a browser preview. You can run the application on your own machine or server, but it sends model requests to Together AI's cloud service. It requires internet access and a Together AI API key, so self-hosting doesn't provide offline model inference.

RAG Web UI is a self-hosted app for asking questions about your own documents. It's a learning project, and its maintainers advise against commercial use and state that it isn't ready for production.

CopilotKit is a self-hostable SDK for developers putting AI agents inside their apps. Its open-source SDK uses MIT, and its enterprise runtime and Intelligence platform can also run on your infrastructure. Copilot Cloud provides managed hosting; where model requests go depends on the agent backend you connect.

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.

DevSpace is a self-hosted MCP server for developers who want ChatGPT, Claude or another compatible client to work in projects on their own machine. It connects an assistant to selected local folders and the project's terminal tools.

HyperWhisper is a desktop speech-to-text app for Windows and Linux that keeps recordings on your computer. It's for people captioning videos, transcribing interviews or podcasts, or turning recordings into searchable text. The interface brings transcription, editing and subtitle export into one place.

Codebase Memory MCP maps a repository's structure so AI coding agents can explore dependencies without repeatedly reading whole files. It's for developers using Claude Code, Codex CLI, Cursor or other MCP-compatible clients.

Bloks is a desktop workspace for people who want personal AI agents working on their own computer. Its messaging-style interface gives agents individual chats and shared rooms for collaborative work.

NativeMind is a local ChatGPT alternative for people who want AI help with reading and writing inside their browser. It processes prompts and page content on your device using local models.

CyberScraper 2077 turns web pages into structured data through a conversational interface. It's for analysts and researchers who want to describe the information they need and export the results.

ComfyUI is a visual AI workflow editor for creators who want control over generation and editing. Its node canvas lets you connect models and processing steps, inspect their settings and reuse the resulting workflows without writing code.

chaiNNer is a desktop editor for people who want AI upscaling and repeatable image processing without writing scripts. Its visual workflows combine model processing with ordinary edits, so you can reuse the same chain across a collection of images.

Humanizer Stack is a pair of Claude Code skills for writers and editors revising public-facing AI drafts. It checks sentence-level habits and the shape of a piece, rather than limiting edits to word substitutions.

Dask-ML is a Python machine learning library for people whose datasets exceed RAM or whose training and evaluation jobs take too long. It uses Dask to distribute work across a cluster of machines, while keeping interfaces familiar to users of Scikit-Learn, NumPy, and pandas. It's open source under the BSD-3-Clause license.

Accentize Chameleon is a proprietary audio plugin that learns a room's reverb from a recording and applies it to dry studio audio. It runs in audio and video hosts on macOS and Windows, and is aimed at post-production engineers matching replacement dialogue (ADR), Foley and effects to location sound.

Wisper is a voice dictation app for people who want to speak into their desktop apps while keeping speech processing on their own computer. It remembers the window where dictation began and inserts the transcript there, even if you switch windows while talking. It can't return to a specific browser tab within that window.

Airux Pocket AI runs AI conversations on Android phones for people who want offline chat and photo analysis without cloud inference. You don't need an account, and downloaded models run directly on your phone.

AgentsMesh coordinates AI coding agents across local machines and servers for developers managing concurrent work. A shared console lets teams assign tasks, watch terminals and follow progress across agents.

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.

Soul-of-Waifu is an AI companion app for creating characters and roleplaying with them. A character carries the same personality and memories between conversations, RPG campaigns and a desktop companion.

Docling turns documents into structured content for developers building search, retrieval and AI applications. It handles page structure and scanned text so applications can work with more than a file's plain text.

LangBot is an AI bot platform for teams handling customer support, internal questions, or community chats. It brings agents and existing AI workflows into the messaging services people already use.

Frigate is a local AI network video recorder for people managing IP security cameras, especially homes using Home Assistant. It identifies people, cars and other objects so recordings and alerts can focus on relevant activity.

FederatedScope is an open-source federated learning platform for researchers and teams building training systems across separate data holders. It can simulate clients and servers on one device or run them as separate distributed participants. Each participant loads its own data, while models can pass between participants through messages.

NVIDIA Container Toolkit lets developers and server operators build and run containers that use NVIDIA GPUs. It provides GPU access for containerized applications on a Linux machine or server.

MemMachine gives developers building AI agents a way to remember earlier conversations and user preferences. Its memory persists across sessions, agents and model changes, so user history can carry over when an application switches models.

Capka is a self-hosted AI agent for people and teams whose work ends in a document, spreadsheet or code patch. It works with uploaded files, runs code and returns editable outputs you can revise through conversation. The app and its Linux sandboxes run on your own server.