OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Obsidian Copilot

Obsidian Copilot is an open-source prototype that connects an Obsidian vault to a retrieval app, using keyword and semantic search to find relevant notes and documents for generated writing or journal reflection.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Obsidian Copilot — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when writing or reflecting in Obsidian would benefit from retrieving relevant material already stored in a vault.

Who it is for

  • Obsidian users who want vault material retrieved as context for drafting section text.
  • Journal writers who want to use daily entries as context for weekly reflection.
  • Developers comfortable configuring a local Docker-based retrieval stack and an Obsidian community plugin.

Documented uses

  • Retrieve relevant notes and documents for a writing section heading.
  • Draft paragraphs using retrieved vault context and inspect the retrieved snippets separately.
  • Reflect on a week using daily journal entries.
Before you choose

Requirements & limits

The project is open source under Apache-2.0. The documented setup requires an API key for the copilot.

  • The setup builds both OpenSearch keyword and semantic indexes from vault content.
  • The retrieval app runs locally through Docker, while the Obsidian plugin connects to it.
  • Setup requires vault and Hugging Face cache paths, a built index, and an API key.
  • Question answering and concise summarization are possible adaptation ideas, not demonstrated documented features.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local retrieval app and Obsidian plugin

Prepare the documented local retrieval workflow and install its plugin; the steps do not cover a successful writing session.

Before you start

  • An Obsidian vault
  • Docker
  • A Hugging Face Hub cache directory
  • A configured API key for the copilot

Steps

  1. Clone the repository and set OBSIDIAN_PATH and TRANSFORMER_CACHE in your shell configuration, retaining the trailing slash on the vault path.

  2. Build the Docker image with make build, start OpenSearch with make opensearch, then build the search artifacts in another terminal with make build-artifacts.

  3. Stop the OpenSearch container and start the retrieval app with make run.

  4. Install the plugin with make install-plugin, enable it in Obsidian's community plugin settings, and configure its API key.

Expected outcome

The documented retrieval service and plugin setup are in place, with keyword and semantic search artifacts built for the vault.

Guide limitations

  • The README says artifact creation can take a while.
  • The guide documents setup, not verification of generated drafts or reflection output.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
eugeneyan/obsidian-copilot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction