Agent Console

⚡

Tabbed Multi-Session

Run several agents side by side in a tabbed sidebar. Tabs, conversations, and scroll position survive an Obsidian restart — and a tab connects to its agent only when you start typing, so reopening your vault never fires up every agent at once.

🤖

Multi-Agent Support

Claude Code, Codex, Gemini CLI, Kiro CLI, or any custom ACP-compatible agent. Use the one you have set up.

📌

Context You Control

A context strip shows exactly what the agent sees. Pin the notes you want and they stay put as you move around your vault, instead of silently changing under you. @mentions, dragged-in images, and slash commands still work.

🎛️

Per-Tab Mode and Model

Switch modes and models per chat without restarting. Each tab remembers its choices.

💻

Terminal Integration

Agents execute shell commands and show output inline in chat. Permission-controlled.

💾

Chat Export

Save sessions as markdown into your vault for future reference and search.

🔍

Session History

Browse past chats and reopen any session in a tab. Fork from any point to explore alternatives.

What is Agent Console?

Agent Console is an Obsidian plugin built on the Agent Client Protocol (ACP). It connects your vault to AI coding agents — Claude Code, Codex, Gemini CLI, Kiro CLI, and custom ACP-compatible agents — and lets you run several at once in a tabbed sidebar, so you can keep working while agents work.

It is a fork of RAIT-09/obsidian-agent-client (Apache-2.0) that adds tabbed multi-session UX and ships as a separately-distributed plugin. See NOTICE for full attribution.

Supported Agents

Agent	Provider	Integration
Claude Code	Anthropic	via ACP adapter
Codex	OpenAI	via Zed's adapter
Gemini CLI	Google	with `--experimental-acp` option
Kiro CLI	Amazon	via built-in ACP support
Custom	Various	Any ACP-compatible agent (e.g., OpenCode, Qwen Code)

Agent

Provider

Integration

Claude Code

Anthropic

via ACP adapter

Codex

OpenAI

via Zed's adapter

Gemini CLI

Google

with --experimental-acp option

Kiro CLI

Amazon

via built-in ACP support

Custom

Various

Any ACP-compatible agent (e.g., OpenCode, Qwen Code)

Why parallel?

AI agents work asynchronously. Tell one to research, another to fix a bug, a third to draft documentation. Switch tabs while they work. Status icons show what each agent is doing — ready, busy, waiting on you, or stuck. Stop the context-switch tax of waiting for one agent before starting the next.

The mental model: tell agents what work to do, not how to do it. With the right skills, agents figure out the steps. You stay focused on the work itself, with several streams progressing at once.

Ready to get started? Check out the Installation Guide.

Agent ConsoleYour Obsidian console for parallel agent work