Terminal session manager for AI coding agents (Claude, Gemini, Aider, OpenCode). Built with Go + Bubble Tea.
<p align="center"> <img src="assets/logo.png" alt="ASMGR Logo" width="200"> </p> <h1 align="center">Agent Session Manager</h1> <p align="center"> A powerful terminal UI (TUI) application for managing multiple AI coding assistant CLI sessions using tmux. </p> <p align="center"> <img src="https://img.shields.io/badge/Go-1.24+-00ADD8?style=flat&logo=go" alt="Go"> <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="License"> </p> --- Inspired by [Gemini Squad](https://github.com/smtg-ai/gemini-squad). ## Supported AI Agents - **Claude Code** - Anthropic's CLI coding assistant - **Gemini CLI** - Google's AI assistant - **Aider** - AI pair programming in your terminal - **OpenAI Codex** - OpenAI's coding assistant - **Amazon Q** - AWS AI coding companion - **OpenCode** - Open-source AI coding assistant - **Custom** - Any CLI command you want to manage ## Features - **Projects/Workspaces** - Organize sessions into separate projects with isolated session lists - **Single Instance Lock** - Only one instance of ASMGR can run per project at a time - **Multi-Agent Support** - Run Gemini, Gemini, Aider, Codex, Amazon Q, OpenCode, or custom commands - **Multi-Session Management** - Run and manage multiple AI sessions simultaneously (multiple sessions can run in the same directory) - **Parallel Sessions** - Start multiple instances of the same session with different names for working on multiple tasks - **Live Preview** - Real-time preview of agent output with ANSI color support and proper wide character handling - **Session Resume** - Resume previous conversations for Gemini, Gemini, Codex, OpenCode, and Amazon Q - **Activity Indicators** - Visual indicators showing active vs idle sessions with per-tab tracking - **Agent Icons** - Toggle display of agent type icons (🤖💎🔧📦🦜💻⚙️) in session list - **Multi-Tab Sessions** - Run multiple agents or terminals within a single session - **Terminal Tabs** - Open shell tabs alongside agent tabs for comman
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.