Analysis updated 2026-05-18
Search your Obsidian notes by meaning instead of exact keywords
Let Claude, ChatGPT, or other MCP tools recall your personal notes
Automatically sync tagged notes to your own Cloudflare server whenever you save
Keep a self-hosted, private AI memory instead of using a third-party note search service
| rahilp/second-brain-obsidian-plugin | 0xradioac7iv/tempfs | abboskhonov/hermium | |
|---|---|---|---|
| Stars | 0 | 0 | 0 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | hard | moderate | moderate |
| Complexity | 3/5 | 3/5 | 4/5 |
| Audience | vibe coder | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires deploying a separate Cloudflare Workers backend before the plugin does anything.
Second Brain Sync is an Obsidian plugin that copies your notes into your own AI memory system so you can search them later using semantic search, meaning search based on meaning rather than exact keyword matches. You can search from inside Obsidian itself or from any AI tool that supports MCP, the Model Context Protocol, which includes assistants like Claude and ChatGPT. The plugin is built to work with a companion project called Second Brain Cloudflare, a separate self-hosted server that runs on Cloudflare Workers and Vectorize, Cloudflare's vector database. Because you deploy and own that Worker yourself, your notes stay on your own infrastructure rather than being sent to a third party service. Before the plugin does anything useful, you need to deploy that Worker first, then connect the plugin to it by entering the Worker's URL and an authentication token in the plugin settings. To choose which notes get synced, you add a tag, brain by default, to a note's frontmatter. From there you can sync a single tagged note with a click or a keyboard shortcut, sync every tagged note at once, or turn on auto-sync so notes upload automatically a few seconds after you stop typing. Long notes are automatically split into overlapping chunks before being turned into embeddings, so a very long note does not dilute the search results, while the overlap between chunks helps preserve context across chunk boundaries. Settings let you control the sync tag, whether auto-sync is on, how long to wait before auto-syncing, chunk size, and how much chunks overlap. The status bar shows when you last synced. The README does not state a software license for the plugin, though the author has a Buy Me a Coffee link for anyone who finds it useful.
An Obsidian plugin that syncs tagged notes to a self-hosted Cloudflare AI memory server for semantic search across Claude, ChatGPT, and other MCP tools.
Mainly TypeScript. The stack also includes TypeScript, Obsidian, Cloudflare Workers.
The README does not state a license.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly vibe coder.
This repo across BitVibe Labs
Verify against the repo before relying on details.