Claude Obsidian

claude-obsidian

**Cowork with Claude inside your [Obsidian](https://obsidian.md) vault.** Chat with your notes as context, let Claude work the vault with its own tools, render interactive artifacts inline, and drive the *same* vault from Claude Code.

[](https://github.com/cavi-ai/claude-obsidian/actions/workflows/obsidian-plugin-ci.yml) [](https://obsidian.md/plugins?id=claude-companion) [](LICENSE)

[**▶ Install the Obsidian plugin**](obsidian://show-plugin?id=claude-companion) · [**Add portable agent workflows**](#getting-it) · [Latest release](https://github.com/cavi-ai/companion-for-claude/releases/latest)

**Open source · MIT · use an Anthropic key or your Claude Code sign-in · local-first**

Chat with your vault	Interactive artifacts

---

What it does

Agent mode

Claude searches, reads, and follows links across the vault while answering, each step shown as a tool chip. Write tools require per-action confirmation. The same agent runs **fully local** on a tool-capable Ollama model (llama3.1, qwen3) — the composer tells you when the selected model lacks tool support. Optional **web search & fetch** tools and **external MCP servers** extend the agent past the vault, both off by default and per-call confirmed. → [agent-mode.md](guides/agent-mode.md