#81 · Primary category: Writing & Content

obsidian-local-gpt

Local Ollama and OpenAI-like GPT's assistance for maximum privacy and offline access

Project last updated:05/02/26

GitHub Stars

675

Forks

61

Contributors

1

License

MIT

Why we included this project

Obsidian users who want AI help without shipping their notes to a cloud service can run this plugin against local models through Ollama or any OpenAI-compatible endpoint. Everything happens on your machine, so it works offline and your vault text never leaves it. Select any passage and pick an action from the context menu or the Action Palette, whether you want to continue a draft, summarize, fix spelling and grammar, or extract action items; you can also write your own system prompts for tasks the defaults don't cover. It pulls context from links, backlinks, and PDFs using embeddings for retrieval-augmented answers, and it accepts images through vision models. A library of community actions, browsable and installable from the settings, extends the built-in set without any coding.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category