Free and open-source AI assistant for Obsidian with Chat, Workflow Automation, and Semantic Search powered by Google Gemini.

This plugin is completely free. You only need a Google Gemini API key (free or paid) from ai.google.dev, or use CLI tools: Gemini CLI, Claude Code, or Codex CLI.

• AI Chat - Streaming responses, file attachments, vault operations, slash commands
• Workflow Builder - Automate multi-step tasks with visual node editor and 21 node types
• Semantic Search - RAG-powered intelligent search across your vault
• Web Search - Access up-to-date information via Google Search
• Image Generation - Create images with Gemini image models

This plugin requires a Google Gemini API key or a CLI tool. You can choose between:

• Rate limits are per-model and reset daily. Switch models to continue working.
• Semantic search sync is limited. Run "Sync Vault" daily - already uploaded files are skipped.
• Gemma models and Gemini CLI don't support vault operations in Chat, but Workflows can still read/write notes using note, note-read, and other node types. {content} and {selection} variables also work.

The AI Chat feature provides an interactive conversation interface with Google Gemini, integrated with your Obsidian vault.

Create reusable prompt templates triggered by /:

• Define templates with {selection} (selected text) and {content} (active note)
• Optional model and search override per command
• Type / to see available commands

Default: /infographic - Converts content to HTML infographic

Reference files and variables by typing @:

• {selection} - Selected text
• {content} - Active note content
• Any vault file - Browse and insert (path only; AI reads content via tools)

Attach files directly: Images (PNG, JPEG, GIF, WebP), PDFs, Text files

The AI can interact with your vault using these tools:

When AI uses propose_edit:

1. A confirmation dialog shows the proposed changes
2. Click Apply to write changes to the file
3. Click Discard to cancel without modifying the file

Changes are NOT written until you confirm.

RAG-powered intelligent vault search:

• Supported files - Markdown, PDF, Images (PNG, JPEG, GIF, WebP)
• Internal mode - Sync vault files to Google File Search
• External mode - Use existing store IDs
• Incremental sync - Only upload changed files
• Target folders - Specify folders to include
• Exclude patterns - Regex patterns to exclude files

Build automated multi-step workflows directly in Markdown files. No programming knowledge required - just describe what you want in natural language, and the AI will create the workflow for you.

You don't need to learn YAML syntax or node types. Simply describe your workflow in plain language:

1. Open the Workflow tab in the Gemini sidebar
2. Select + New (AI) from the dropdown
3. Describe what you want: "Create a workflow that summarizes the selected note and saves it to a summaries folder"
4. Click Generate - the AI creates the complete workflow

Modify existing workflows the same way:

1. Load any workflow
2. Click the AI Modify button
3. Describe changes: "Add a step to translate the summary to Japanese"
4. Review and apply

You can also write workflows manually. Add a workflow code block to any Markdown file:

```workflow
name: Quick Summary
nodes:
  - id: input
    type: dialog
    title: Enter topic
    inputTitle: Topic
    saveTo: topic
  - id: generate
    type: command
    prompt: "Write a brief summary about {{topic.input}}"
    saveTo: result
  - id: save
    type: note
    path: "summaries/{{topic.input}}.md"
    content: "{{result}}"
    mode: create
```

Open the Workflow tab in the Gemini sidebar to run it.

21 node types are available for building workflows:

For detailed node specifications and examples, see WORKFLOW_NODES.md

Assign keyboard shortcuts to run workflows instantly:

1. Add a name: field to your workflow
2. Open the workflow file and select the workflow from dropdown
3. Click the keyboard icon (⌨️) in the Workflow panel footer
4. Go to Settings → Hotkeys → search "Workflow: [Your Workflow Name]"
5. Assign a hotkey (e.g., Ctrl+Shift+T)

When triggered by hotkey:

• prompt-file uses the active file automatically (no dialog)
• prompt-selection uses the current selection, or full file content if no selection

Workflows can be automatically triggered by Obsidian events:

Event trigger setup:

1. Add a name: field to your workflow
2. Open the workflow file and select the workflow from dropdown
3. Click the zap icon (⚡) in the Workflow panel footer
4. Select which events should trigger the workflow
5. Optionally add a file pattern filter

File pattern examples:

• **/*.md - All Markdown files in any folder
• journal/*.md - Markdown files in journal folder only
• *.md - Markdown files in root folder only
• **/{daily,weekly}/*.md - Files in daily or weekly folders
• projects/[a-z]*.md - Files starting with lowercase letter

Event variables: When triggered by an event, these variables are set automatically:

Note: prompt-file and prompt-selection nodes automatically use the event file when triggered by events. prompt-selection uses the entire file content as the selection.

1. Install BRAT plugin
2. Open BRAT settings → "Add Beta plugin"
3. Enter: https://github.com/takeshy/obsidian-gemini-helper
4. Enable the plugin in Community plugins settings

1. Download main.js, manifest.json, styles.css from releases
2. Create gemini-helper folder in .obsidian/plugins/
3. Copy files and enable in Obsidian settings

git clone https://github.com/takeshy/obsidian-gemini-helper
cd obsidian-gemini-helper
npm install
npm run build

1. Get API key from ai.google.dev
2. Enter in plugin settings
3. Select API plan (Free/Paid)

Gemini CLI:

1. Install Gemini CLI
2. Authenticate with gemini → /auth
3. Click "Verify" in Gemini CLI section

Claude CLI:

1. Install Claude Code: npm install -g @anthropic-ai/claude-code
2. Authenticate with claude
3. Click "Verify" in Claude CLI section

Codex CLI:

1. Install Codex CLI: npm install -g @openai/codex
2. Authenticate with codex
3. Click "Verify" in Codex CLI section

CLI Limitations: Read-only vault operations, no semantic/web search

• Workspace Folder - Chat history and settings location
• System Prompt - Additional AI instructions
• Tool Limits - Control function call limits
• Slash Commands - Define custom prompt templates

• Click Gemini icon in ribbon
• Command: "Gemini Helper: Open chat"
• Toggle: "Gemini Helper: Toggle chat / editor"

• Enter - Send message
• Shift+Enter - New line
• Stop button - Stop generation
• + button - New chat
• History button - Load previous chats

1. Open Workflow tab in sidebar
2. Open a file with workflow code block
3. Select workflow from dropdown
4. Click Run to execute
5. Click History to view past runs

Export to Canvas: View execution history as an Obsidian Canvas for visual analysis.

Create New Workflow with AI:

1. Select + New (AI) from the workflow dropdown
2. Enter workflow name and output path (supports {{name}} variable)
3. Describe what the workflow should do in natural language
4. Select a model and click Generate
5. The workflow is automatically created and saved

Modify Existing Workflow with AI:

1. Load an existing workflow
2. Click the AI Modify button (sparkle icon)
3. Describe the changes you want
4. Review the before/after comparison
5. Click Apply Changes to update

Manual Workflow Editing:

Edit workflows directly in the visual node editor with drag-and-drop interface.

Reload from File:

• Select Reload from file from the dropdown to re-import workflow from the markdown file

• Obsidian v0.15.0+
• Google AI API key, or CLI tool (Gemini CLI / Claude CLI / Codex CLI)
• Desktop and mobile supported (CLI mode: desktop only)

Data stored locally:

• API key (stored in Obsidian settings)
• Chat history (as Markdown files)
• Workflow execution history

Data sent to Google:

• All chat messages and file attachments are sent to Google Gemini API for processing
• When Semantic Search is enabled, vault files are uploaded to Google File Search
• When Web Search is enabled, queries are sent to Google Search

Data sent to third-party services:

• Workflow http nodes can send data to any URL specified in the workflow

CLI providers (optional):

• When CLI mode is enabled, external CLI tools (gemini, claude, codex) are executed via child_process
• This only occurs when explicitly configured and verified by the user
• CLI mode is desktop-only (not available on mobile)

Security notes:

• Review workflows before running - http nodes can transmit vault data to external endpoints
• Workflow note nodes show a confirmation dialog before writing files (default behavior)
• Slash commands with confirmEdits: false will auto-apply file edits without showing Apply/Discard buttons

See Google AI Terms of Service for data retention policies.

MIT

• Gemini API Docs
• Obsidian Plugin Docs

If you find this plugin useful, consider buying me a coffee!