# AI use cases for Obsidian Mind (breferrari/obsidian-mind)

Repo: [breferrari/obsidian-mind](https://github.com/breferrari/obsidian-mind) | Use cases: 3 | Page: https://dedupedai.com/use-cases/breferrari-obsidian-mind/

Obsidian Mind is an Obsidian vault template that gives AI coding agents persistent memory through hooks, slash commands and optional local QMD semantic search, built for Claude Code with hooks for Codex CLI and Gemini CLI.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Give your coding agent a memory that compounds: https://dedupedai.com/use-cases/breferrari-obsidian-mind/give-agent-persistent-memory-vault/
- Run a daily standup and brain dump with your agent: https://dedupedai.com/use-cases/breferrari-obsidian-mind/daily-standup-and-brain-dump-commands/
- Add offline semantic search to the vault: https://dedupedai.com/use-cases/breferrari-obsidian-mind/add-local-semantic-search-to-vault/

## How to give your coding agent a memory that compounds with Obsidian Mind

Repo: [breferrari/obsidian-mind](https://github.com/breferrari/obsidian-mind) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install the vault, open it in Obsidian, and run your agent inside it so every session builds on the last.

**Who it is for:** An engineer tired of re-explaining projects and decisions every session.

**The problem:** Agents start from zero each session.

**The outcome:** A vault the agent reads and updates with notes, links and indexes.

### Steps

1. Install with `npm install -g shardmind` then `shardmind install github:breferrari/obsidian-mind` in a fresh folder
2. Open the folder as an Obsidian vault
3. Run `claude` in the vault directory
4. Say start session and talk about your day

### Prompt to paste into your agent

```text
Install breferrari/obsidian-mind with ShardMind, run Claude Code in the vault, and say start session. Report what context the agent loaded and confirm new notes were created.
```

### Caveat

Codex runs the vault hooks only after the folder is trusted and each hook approved.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/breferrari-obsidian-mind/give-agent-persistent-memory-vault/

## How to run a daily standup and brain dump with your agent with Obsidian Mind

Repo: [breferrari/obsidian-mind](https://github.com/breferrari/obsidian-mind) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Use /om-standup to load priorities and /om-dump to file meeting notes, decisions and wins.

**Who it is for:** An engineering manager juggling 1:1s, projects and decisions.

**The problem:** Meeting notes and decisions scatter across tools.

**The outcome:** Updated people, project and decision notes from one dump.

### Steps

1. Install the vault and start your agent in it
2. Run /om-standup each morning
3. After meetings run /om-dump with what happened
4. Review the updated notes in Obsidian

### Prompt to paste into your agent

```text
In obsidian-mind, run /om-standup, then /om-dump <meeting notes>. List the notes the agent created or updated and confirm each decision was recorded.
```

### Caveat

The quality of recall depends on what you dump into it.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/breferrari-obsidian-mind/daily-standup-and-brain-dump-commands/

## How to add offline semantic search to the vault with Obsidian Mind

Repo: [breferrari/obsidian-mind](https://github.com/breferrari/obsidian-mind) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Install QMD so the agent and subagents search your notes semantically with local models.

**Who it is for:** A heavy vault user whose grep searches miss relevant notes.

**The problem:** Keyword search misses notes with different wording.

**The outcome:** Local semantic search exposed to the agent via MCP.

### Steps

1. Run `npm install -g @tobilu/qmd`
2. Run `node --experimental-strip-types .scripts/qmd-bootstrap.ts`
3. Query with `qmd --index obsidian-mind query "what did we decide about caching"`
4. Re-run update or embed after bulk edits

### Prompt to paste into your agent

```text
Install QMD for obsidian-mind, bootstrap the index, and query <question>. Confirm the top results are relevant notes and that no API key was used.
```

### Caveat

QMD downloads small local models, including a 1.28 GB query expansion model.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/breferrari-obsidian-mind/add-local-semantic-search-to-vault/