Obsidian Local GPT is a plugin that embeds AI assistance directly into the Obsidian knowledge management environment while prioritizing privacy and local execution. It supports both local models through Ollama and OpenAI-compatible APIs, allowing users to choose between fully offline workflows or hybrid setups. The plugin introduces an “Action Palette” system that enables users to run predefined or custom AI-powered actions on selected text, notes, or entire documents. It integrates deeply with Obsidian’s structure by pulling context from backlinks, linked notes, and even external files like PDFs to enhance responses. The system also supports multimodal capabilities, including image analysis when paired with compatible models. Users can create reusable prompts, install community-provided actions, and manage workflows directly inside their note-taking environment.

Features

  • Local-first AI assistance with Ollama support
  • Context-aware responses using linked notes and files
  • Action Palette for reusable AI workflows
  • Vision support for image analysis in notes
  • Community action library with auto-updates
  • Multilingual support with automatic detection

Project Samples

Project Activity

See All Activity >

Categories

Code Editors

License

MIT License

Follow Obsidian Local GPT

Obsidian Local GPT Web Site

Other Useful Business Software
Build Agents and Models on One Platform Icon
Build Agents and Models on One Platform

Everything you need to build production-ready agents and models. Access 200+ Google and third-party AI models and tools.

Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Start Free
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of Obsidian Local GPT!

Additional Project Details

Programming Language

TypeScript

Related Categories

TypeScript Code Editors

Registered

2026-04-20