Best open-source AI & Machine Learning projects

Open-source, fully local voice studio for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation in 646 languages.

Open-source agentic video production system that turns an AI coding assistant into a pipeline-driven video studio for research, scripting, asset generation, and rendering.

Turns your exported chat history into a fine-tuned LLM that mimics your writing style, then deploys it as a chatbot on messaging platforms.

Windows-focused Gradio web app for dubbing workflows: YouTube download, vocal separation, Whisper subtitles, translation, and TTS with voice cloning.

Converts static images of diagrams, flowcharts and formulas into fully editable DrawIO (XML) files using SAM 3 segmentation and OCR.

An open-source AI agent app for iOS and Android that runs models like Claude and GPT with an on-device Linux shell, browser automation and device integrations.

A Zotero plugin that lets you chat with one PDF, several PDFs, or your whole library, with clickable citations and optional fully local models.

Real-time two-way speech translation app for bilingual meetings, with cloud providers or fully offline on-device inference, for desktop and Chrome/Edge.

A Windows portable package that runs the Hunyuan3D 2.0 and 2.1 image-to-3D Gradio web apps without manual environment setup.

A native AI chat client for iPhone, iPad, and Mac that connects to cloud, self-hosted, and on-device models.

Self-hosted gateway that connects phone lines and chat channels to AI agents, using your own API keys.

Local, offline voice processing tool combining TTS, voice cloning, voice conversion, music generation, STT, and speech enhancement in one CLI/GUI.

Self-hostable open-source legal OS for drafting, reviewing, and managing contracts, with an AI assistant called Luna.

A local-first desktop AI agent that operates your Windows PC, browser, and files, controllable from the terminal, desktop app, or Telegram.