Bring AI agents into Obsidian via Agent Client Protocol (ACP), such as Claude Code, Codex, and Gemini CLI. Operations teams can automate workflows, generate code, and process data directly within Obsidian. Connects to AI agents and integrates with Obsidian's plugin ecosystem.
git clone https://github.com/RAIT-09/obsidian-agent-client.githttps://rait-09.github.io/obsidian-agent-client/
["Install the obsidian-agent-client plugin in Obsidian via the Community Plugins tab.","Configure the plugin with your preferred AI agent (e.g., Claude Code, Codex, or Gemini CLI) by setting the API keys in the plugin settings.","Open the Obsidian command palette (Ctrl/Cmd+P) and run 'ACP: Run Agent Command' to execute a predefined task or use the prompt template to customize your request.","For complex workflows, create a markdown file in your vault with the task details and reference it in your prompt (e.g., 'Process the data in [FILE_NAME] and generate a summary').","Review the output in your vault and iterate by refining the prompt or adjusting the agent's parameters for better results."]
Automate note-taking by querying AI agents for information and saving responses directly as Markdown notes.
Execute terminal commands through AI agents to retrieve data or perform actions without switching applications.
Switch between different AI models seamlessly to leverage their unique capabilities for various tasks.
Maintain a history of conversations with AI agents to revisit and build upon previous discussions.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/RAIT-09/obsidian-agent-clientCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Use the obsidian-agent-client to [TASK] in Obsidian. For example: 'Run a Python script to analyze [DATASET] in my vault and append the results to [FILE_NAME].' or 'Generate a weekly report by querying my task database and summarizing overdue items.' Include any specific requirements like [OUTPUT_FORMAT] or [AGENT_TO_USE].
```markdown # Weekly Task Analysis Report (Generated via obsidian-agent-client) **Generated on:** 2024-06-14 **Agent used:** Claude Code (claude-3-opus-20240229) ## 📊 Task Overview - **Total tasks:** 42 - **Completed:** 35 (83%) - **Overdue:** 5 - **Due this week:** 2 ## 🚨 Critical Overdue Tasks 1. **Update API documentation** (Due: 2024-06-10) - Owner: @dev-team - Priority: High - Status: Blocked by pending review - Suggested action: Schedule urgent review with @tech-lead 2. **Fix login timeout issue** (Due: 2024-06-12) - Owner: @backend-team - Priority: Critical - Status: In progress - Suggested action: Deploy patch to staging by EOD ## 📝 Notes - The analysis was performed on tasks stored in `Tasks/2024-Q2.md` using Python (pandas for data processing). - Overdue tasks were identified by comparing due dates with today's date. - The report was automatically appended to `Reports/Weekly-Task-Analysis.md` in the vault. --- *Generated automatically via obsidian-agent-client. Next scheduled run: 2024-06-21.* ```
Google's multimodal AI model and assistant
AI assistant built for thoughtful, nuanced conversation
Knowledge-powered CRM with networked thinking
IronCalc is a spreadsheet engine and ecosystem
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan