DevOps Agent
AI CI/CD, infra, deployment
Frontend Agent
AI UI/UX, components
Backend Agent
AI API, database, perf
Architect Agent
AI system design, refactoring
QA Agent
AI testing, edge cases, quality
Fullstack Agent
AI end-to-end development
Mobile Agent
AI iOS, Android, React Native
Security Agent
AI security audit, vulnerabilities
PM Agent
AI specs, priorities, coordination
Marketing Agent
AI copy, SEO, landing pages
Git Expert Agent
AI branch management, workflows
SEO Agent
AI rankings, structured data, CWV
All your agents
Claude
one screen.
All your Claude, Codex, Gemini CLI, OpenCode and Aider agents in one screen. AgentsRoom supports multiple AI coding providers.You already run AI agents in your terminal. AgentsRoom gives you a visual interface to manage Claude, Codex, Gemini CLI, OpenCode and Aider sessions at once. See who's coding, who's done, who needs you.
AgentsRoom
Side Projects/Users/cegedim/Documents/Perso/…
your agents run in parallel, you keep a clear head — the UI sorts it out, your mind stays sharp
What AgentsRoom does for you
From status tracking to prompt management. Every feature is designed to save you time and keep you in control of your agents.
See who is working, right now
Color-coded status indicators on every agent card. Yellow pulsing dot when thinking, green when done, red when waiting for your input. Elapsed time and current activity displayed in real time.
Control your agents from your phone
Start agents, type in the terminal, send prompts, and monitor progress from your iPhone or Android. Real-time sync with end-to-end encryption between your desktop and your mobile device.
Share localhost with a public HTTPS URL
Expose your local dev server to the internet instantly. Pick a custom subdomain, get a public HTTPS link, and share your work with anyone — no deploy needed. Free ngrok alternative built into AgentsRoom.
Diff per agent & task
When multiple agents work in parallel, filter code changes by agent. See only one agent's modifications, review their diffs in isolation, and commit each contribution separately. Clean git history, zero confusion.
Drag a task, spawn an agent
Kanban board for your AI agents. Create tasks, drag them to In Progress, and an agent starts working immediately. Track every feature visually — who does what, what is done, what is next.
Know exactly which agent finished
Unread indicators per project and per agent, like a messaging app. macOS and mobile push notifications when an agent completes or needs input. No more guessing.
Save and reuse your best prompts
Organize prompts in folders, per project. Share them with your team via git. Keep personal prompts private with automatic gitignore. Send any prompt to an agent in one click.
Review all changes, file by file
Navigate every file modified by your AI agents with arrow keys. See side-by-side diffs with syntax highlighting. Ask Claude questions about any change. Commit when you are ready.
A project terminal you drive from your pocket
A real per-project terminal manager built into AgentsRoom. Remember every command (backend, frontend, mobile bundler, Docker, worker, database) and launch them in one click. Detach the window onto a second monitor, or trigger commands from mobile over 4G/5G — your Mac becomes a dev server you drive remotely. The modern alternative to iTerm2, Warp, Ghostty, Kitty, Alacritty, WezTerm, Hyper, Tabby and Terminal.app, designed for project work.
Switch between Claude, Codex, Gemini, OpenCode & Aider
Use 5 AI coding providers in the same project. Pick a provider per agent, switch mid-conversation, and keep your full context with automatic handoff. Claude, Codex, OpenCode, Gemini CLI, Aider — all in one app.
Your terminal, with a visual layer on top.
Same CLI tools you already use: Claude, Codex, OpenCode, Gemini CLI, Aider. AgentsRoom wraps each session in a real terminal with project organization, role labels, status tracking and notifications. Nothing changes in how your tools work.
A visual layer your agents deserve
Each agent gets an avatar, a role label, and a colored status indicator. Projects show live activity rings. You see the state of your entire fleet at a glance, not buried in terminal tabs. The interface is designed to make parallel work readable.
Work across projects in parallel
Organize your repos by zone (Work, Personal, Side projects) with drag and drop. Switch between projects in one click. Each project has its own agents, its own backlog, its own config. Run agents on three projects at the same time without losing track.
Control your agents from your phone
The companion app (iOS and Android) connects to your desktop via end-to-end encrypted sync. Start agents, type in terminals, send prompts, and monitor status from anywhere. Your commute becomes productive coding time.
Access localhost from anywhere
Expose your local dev server through AgentsRoom's own built-in secure tunnel with one click. Test your agents' frontend work on your phone while commuting. Share a live preview link with a colleague for instant feedback. No port forwarding, no ngrok config.
Prompt library with local and global scopes
Save your best prompts and organize them in folders. Project-scoped prompts are shared between all team members through git. Global prompts follow you across all your projects. Send any prompt to a running agent with one tap on mobile or one click on desktop.
Task-driven development with visual backlog
Write all your tasks in a kanban board. Drag a card to In Progress and a new agent spawns with the task as its prompt. Run as many agents in parallel as your machine allows. Your brain stays clear, your backlog stays organized, your agents stay busy.
File changes isolated per agent
When five agents work in parallel, you need to know exactly what each one changed. AgentsRoom shows a per-agent diff view so you review changes by feature, not as a tangled mess. Approve, revert, or commit each agent's work independently.
A real IDE, not just a terminal wrapper
Browse your project files, view code with syntax highlighting, git pull, git push, manage branches. Edit CLAUDE.md, permissions and hooks without leaving the app. AgentsRoom is the only interface you need open while your agents work.
Switch providers mid-conversation
Start a task with Claude Opus for deep reasoning, switch to Codex for rapid iteration, then to Gemini CLI for a different perspective. The conversation context carries over. Useful if you have multiple subscriptions or want to compare outputs on the same task.
Git worktree isolation per agent
Each agent can work in its own git worktree, a fully isolated copy of your repo on a separate branch. No merge conflicts between agents. Review and merge each branch when ready. Clean separation for complex parallel workflows.
Built-in AI tools for productivity
Beyond agent management, AgentsRoom includes tools to help you work faster: generate commit messages from diffs, get code explanations, refactor selections, and more. Small utilities that save minutes throughout the day.
Notifications that respect your flow
macOS alerts when an agent finishes, encounters an error, or waits for input. Dock badge shows unread count. Push notifications on your phone via the mobile app. You never have to poll terminals to check if something is done.
Go touch grass.
Your agents got it.
Grab a coffee, take a walk, or just breathe while AgentsRoom keeps 8 specialized AI agents shipping code, writing tests, and reviewing PRs in parallel.
Actual footage: 8 agents running live on 4 projects while taking a coffee break
Companion app: monitor your agents on the go
Works with Claude, Codex, OpenCode, Gemini CLI, and Aider
3 things. That's it.
Your projects
Each project = a real folder on your machine. Group them by zone: Work, Personal, Side-projects. See at a glance which ones have active agents.
Your agents
Label each agent session with a role: DevOps, Frontend, QA, Architect... Each one gets its own terminal, its own system prompt, and runs the provider and model you pick.
Everything, live
See who's working, who's done, who's stuck. Get a macOS notification when an agent finishes. Click, give a new instruction, and keep going.
AgentsRoom vs the alternatives
Most tools wrap tmux and support a single provider. AgentsRoom gives you a real visual interface with multi-provider support.
13 roles to organize your agents.
Each role is a label with a tuned system prompt. Assign one to any AI agent session (Claude, Codex, OpenCode, Gemini CLI, Aider) so you know at a glance who does what. Create your own roles too.
Works with your favorite AI coding tools
Pick a different provider for each agent. Switch mid-conversation without losing context.
Claude Code
Anthropic
Anthropic's CLI for code generation, launched in 2025. Strong at complex reasoning, large codebase navigation, and long multi-step tasks. Supports Opus, Sonnet, and Haiku models.
Codex CLI
OpenAI
OpenAI's open-source terminal agent, released in 2025. Runs GPT-4.1 and o3 models locally. Offers a full-auto mode for hands-free coding with sandboxed execution.
OpenCode
Open Source
Community-driven open-source terminal agent. Supports multiple LLM backends (OpenAI, Anthropic, local models). Configurable via YAML files with a focus on extensibility.
Gemini CLI
Google's official CLI agent for Gemini models, released in 2025. Free tier with 60 requests per minute. Integrates with Google Cloud services and supports Gemini 2.5 Pro.
Aider
Open Source
Established open-source pair programming tool, active since 2023. Works with most LLM providers. Known for its git integration and architect/editor workflow pattern.
One app, every provider
AgentsRoom spawns the CLI of each provider natively. Assign Claude to your architect agent, Codex to your backend agent, and Aider to your reviewer. Switch provider on any agent mid-conversation and keep the full context. No lock-in, no wrapper, no proxy.
Built for the workflow
Built-in terminal
Full terminal per agent. 10K lines scrollback. Syntax colors. Clickable links.
macOS notifications
Get notified when an agent finishes or gets stuck. Dock badge shows unread count.
Edit CLAUDE.md from the app
Change project context, permissions, and hooks without opening your editor.
Prompt Library
Save your best prompts per project. Organized in folders, committed to git, personal ones gitignored.
Provider and model per agent
Claude Opus for the architect. Codex for the backend. OpenCode for a quick fix. Mix providers freely.
Organize by zones
Drag projects between zones. Group by client, team, or priority.
100% local
Your agents run on your machine via the CLI of your choice. Your code never leaves your disk.
Mobile Companion
Monitor all your agents from your phone. Get notified when they finish or need help.
FAQ
Try it. 30 seconds.
Download AgentsRoom. Create a project. Launch your first agent. That's it.
Free. No credit card required.
Works with Claude, Codex, OpenCode, Gemini CLI, and Aider