Obsidian plugin that adds an AI agent chat sidebar with vault CRUD capabilities. Supports Claude Code, OpenAI Codex, Google Gemini, and GitHub Copilot via CLI or API.
# AI Agent Sidebar for Obsidian An Obsidian plugin that adds a sidebar where you can chat with AI agents (Claude Code, OpenAI Codex, Google Gemini, GitHub Copilot, and any OpenAI-compatible endpoint) and have them read, create, edit, rename, and delete files in your vault. Agents can be used via their CLI tools or directly through their APIs. ## TL;DR 1. **Get access to at least one agent** — either install a CLI tool or grab an API key: - [Claude Code CLI](https://docs.anthropic.com/en/docs/claude-code) or [Anthropic API key](https://console.anthropic.com) → see [API Keys](#api-keys) - [OpenAI Codex CLI](https://github.com/openai/codex) or [OpenAI API key](https://platform.openai.com) → see [API Keys](#api-keys) - [Google Claude API key](https://aistudio.google.com) (API only) → see [API Keys](#api-keys) - [GitHub Copilot CLI](https://docs.github.com/en/gemini/github-gemini-in-the-cli) (CLI only) - A local [Ollama](https://ollama.com), vLLM, or LM Studio server 2. **Install the plugin**: - Download `main.js`, `manifest.json`, and `styles.css` from the [latest release](https://github.com/coreydaley/obsidian-ai-agent-sidebar-plugin/releases/latest) - Copy all three files into `<your-vault>/.obsidian/plugins/obsidian-ai-agent-sidebar/` - In Obsidian: **Settings → Community Plugins → enable "AI Agent Sidebar"** 3. **Open the sidebar** from the ribbon icon or **Ctrl/Cmd+P → "Open AI Agent Sidebar"** and start chatting. --- ## Features - **Multi-agent tabs**: Switch between enabled agents without losing conversation history - **CLI and API modes**: Use agents via their installed CLI tools or directly via API key - **OpenAI-compatible endpoint support**: Connect to any OpenAI-compatible server (Ollama, vLLM, LM Studio, etc.) - **Vault CRUD**: Agents can read, create, edit, rename, and delete your notes - **Streaming responses**: See responses token-by-token as they arrive - **Auto-context**: The currently open note is automatically shared
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.