The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Harness LLMs with Multi-Agent Programming

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini) and includes benchmark tools to test on your own setup. Searches 10+ sources - arXiv, PubMed, GitHub, web, and your private documents. Everything Local.

Chat Multiple PDFs in Zotero AI with Gemini, Grok 4, DeepSeek, GPT, ChatGPT, Claude, OpenRouter, Gemma 3, Qwen 3

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

A simple "Be My Eyes" web app with a llama.cpp/llava backend

Run AI ✨ assistant locally! with simple API for Node.js 🚀

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

A local, privacy-first résumé builder using LLMs and Markdown to generate ATS-ready DOCX files with Pandoc — no cloud, no tracking.

Chrome Extension to Summarize or Chat with Web Pages/Local Documents Using locally running LLMs. Keep all of your data and conversations private. 🔐

A simple, intuitive toolkit for quickly implementing LLM powered applications.

Code with AI in VSCode, bring your own ai.

Your fully proficient, AI-powered and local chatbot assistant🤖

React Native Apple LLM plugin using Foundation Models

Local coding agent with neat UI

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

LLM story writer with a focus on high-quality long output based on a user provided prompt.

A python package for developing AI applications with local LLMs.

Custom TTS component for Home Assistant. Utilizes the OpenAI speech engine or any compatible endpoint to deliver high-quality speech. Optionally offers chime and audio normalization features.

A text-based user interface (TUI) client for interacting with MCP servers using Ollama. Features include multi-server, dynamic model switching, streaming responses, tool management, human-in-the-loop, thinking mode, full model parameters configuration, custom system prompt and saved preferences. Built for developers working with local LLMs.