AQ

AQ

AQ is a multiplayer agentic development environment that lets engineering teams run AI coding agents (Claude Code, Codex, Cursor, etc.) together with shared live terminals, a collaborative code editor, and live app previews, running on your own cloud, a dedicated AQ-managed VM, or a free personal sandbox.

AQ is ai agents software teams evaluate for software & gaming. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Freemium API Enterprise 80/100
One of 608 tools in AI Agents
Added 1 month ago
Data reviewed Sep 3, 2026

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: Software & Gaming

What it does

AI Agents software for decision-makers comparing workflow fit and alternatives.

Best fit

Software & Gaming

Pricing snapshot

Freemium from No seat charge; includes a private AQ-managed sandbox and $5 in AQ model credits

Next step

Compare AQ with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

AQ is a multiplayer, agentic development environment designed for engineering teams to run AI coding agents collaboratively. It provides shared live terminals, a collaborative code editor, persistent workspaces, and live app previews that stream from the running dev server. AQ runs where you are: on VMs in your own cloud, on a dedicated AQ-managed VM, or in a free AQ-managed personal sandbox, and it emphasizes running agents with each person's own accounts and dedicated execution infrastructure rather than multi-tenant shared runtime.

AQ targets engineers, product managers, and designers working together with coding agents: it supports real agent CLIs (Claude Code, Codex, Cursor, etc.), integrates with team workflows (Linear and Git/GitHub-based PRs), and offers features for parallel isolated workspaces, persistent sessions, and live review to streamline from issue to pull request.

AQ is the multiplayer agentic development environment: your whole team and every agent CLI in live shared workspaces, on infrastructure you control.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

Multiplayer live terminals & shared keyboard

Teammates open a workspace and watch the same live terminal; one-click handoff lets someone type as you while you retain your own input and you can revoke control at any time.

Isolated git worktrees per task

Each task gets its own isolated git worktree so parallel agents and workspaces don't interfere; dependencies install automatically and you can rebase onto main with one click.

Persistent sessions (tmux) and parallel workspaces

Sessions run in persistent tmux on the VM so work continues when devices disconnect; parallel workspaces allow concurrent tasks on the same repository.

Live app previews & shareable links

A workspace can run its dev server and stream the running app next to the agent; Team plan supports shareable preview links that open without an account for viewing and support pinned comments on the page.

Agent CLI integration

Supports signing in to agent CLIs (Claude Code, Codex, Cursor Agent and others) with each person’s own accounts; agents can commit, push, and open pull requests using each person's GitHub auth.

Flexible execution: sandbox, managed VM, or your cloud

Run on a private AQ-managed sandbox (free), a dedicated AQ-managed VM for teams, or connect VMs from your own cloud account; AQ states it does not use shared multi-tenant execution infrastructure.

AQ Models and credits

During early access, AQ provides a free sandbox with $5 in AQ model credits and offers AQ Models (e.g., GLM 5.2) that consume AQ credits when used through AQ’s gateway.

Linear integration and PR workflow

Label a Linear issue ai-task to create a workspace tracked in the team sidebar; work and PR status sync both ways and agents produce PRs using each person's GitHub credentials.

Pricing

Free Tier Available

Personal AQ-managed sandbox with no seat charge and $5 in AQ model credits; model usage is separate from the free sandbox.

Free (Early access personal sandbox)

No seat charge; includes a private AQ-managed sandbox and $5 in AQ model credits
  • One-person private AQ-managed sandbox
  • Nothing to install
  • $5 in AQ credits for AQ Models (model usage separate from agent subscriptions)

Team (Early access)

$50 per user per month (during early access)
  • Adds teammates and sharing
  • Choice of VMs in your own cloud or a dedicated, always-on VM managed by AQ
  • Shareable live previews and team features

Use Cases

Collaborative agent-driven coding

Teams run AI coding agents together while multiple people observe, steer, and step into live terminals and editors.

Agent-assisted code review

Use agents to review code and have teammates step into the same live session to address findings together.

Paired debugging and onboarding

Debugging together with live terminals and app previews, and onboarding engineers by giving them a persistent sandboxed workspace.

Issue-to-PR workflow

Label Linear issues to spawn workspaces, let agents work and commit, and produce pull requests tracked back to the workspace for a direct path from issue to PR.

Integrations

Claude Code / OpenAI (Codex) / Cursor / other agent CLIs

Sign in to these agent CLIs with your own accounts to run agents inside AQ; AQ does not proxy or mark up usage from those agent subscriptions.

AQ Models (e.g., GLM 5.2)

AQ provides its own models accessed through AQ's gateway which consume AQ credits; available as an alternative to using personal agent subscriptions.

Linear

Label a Linear issue ai-task to create a tracked workspace; status syncs both ways as work moves between Linear and the workspace.

GitHub

Agents commit, push, and open pull requests using each person's GitHub authentication so PRs originate under individual accounts.

Benefits

Enables live, multiplayer collaboration in the same terminal and editor to reduce handoffs and speed decisions
Runs on dedicated infrastructure (your cloud or AQ-managed VMs) with persistent sessions so work survives device disconnects
Isolated git worktrees and parallel workspaces prevent agents from stepping on each other's changes
Supports real agent CLIs and personal agent accounts, and AQ does not mark up model usage from those accounts
Live app previews with shareable links make reviewing running apps immediate and contextual

Limitations

Early access requires personal review and approval for sign-ups; requests are reviewed and you may be added to a queue.
Model usage is separate from the Free plan — using some agents (Claude, OpenAI Codex) requires individual subscriptions, or you can consume AQ credits with AQ Models.
Some sharing/viewing features (e.g., link-based viewer without account) are described as Team plan capabilities.

Frequently Asked Questions

What is included in the Free plan?
AQ's Free plan has no seat charge and gives one person a private, AQ-managed sandbox with nothing to install. Model usage is separate: use your own agent subscriptions, or use AQ Models with AQ credits. The Team plan adds teammates and sharing, plus your choice of VMs in your own cloud or a dedicated, always-on VM managed by AQ.
Do I need my own Claude or OpenAI subscription?
Only if you want to use Claude Code or Codex. Each person signs in to those CLIs with their own Claude or OpenAI account, and AQ does not proxy or mark up that usage. You can instead run OpenCode or Pi with AQ Models such as GLM 5.2 which consume AQ credits through AQ's gateway.
Where does my code run?
With the Free plan, your code runs on a private AQ-managed VM dedicated to you. With the Team plan, it runs either on VMs you connect from your own cloud account or on a dedicated AQ-managed VM. Checkout, worktrees, shell sessions, and CLI credentials stay on that VM; AQ does not use shared multi-tenant execution infrastructure. Model inference is separate and may go through the model provider or AQ's gateway when using AQ Models.
Is AQ an agentic development environment?
Yes: workspaces as the task surface, one isolated git worktree per task, the real agent CLIs as the runtime, a live terminal and editor for stepping in, and pull requests out the other side. The difference from desktop ADEs is that AQ sessions are multiplayer and run on machines dedicated to you instead of one person's laptop.
What happens when I click “Start free”?
You accept the Terms of Service and continue with a work Google account. If you are not already approved, AQ adds you to the review queue; requests are reviewed personally and AQ emails you when your workspace is ready. Then sign in, connect an agent, and add your first project.

Getting Started

  1. 1 Step 1: Connect an environment — start free in the personal sandbox AQ creates for you, or subscribe to run on your own cloud or a dedicated AQ-managed VM.
  2. 2 Step 2: Sign in to your agents — authenticate Claude Code, Codex, Cursor Agent, or other agent CLIs with your existing agent accounts (AQ does not proxy or mark up that usage).
  3. 3 Step 3: Build together live — open workspaces (one git worktree per task), use shared live terminals and the editor, run the dev server for live previews, and invite teammates with a link.

Support

Sales / Inquiries

Talk to sales link available on the site (https://aq.dev/).

Email

AQ emails users when workspaces are ready and uses work-email sign-in; requests are personally reviewed.

Documentation

Docs and API guides are listed in the site navigation (Docs, API, Guides).

API

Available: Yes
Documentation:

API and Guides referenced in site navigation (see https://aq.dev/)

Compare AQ with similar tools

See how it stacks up against alternatives

Related Tools

View all 608 →
Free
Offrun

Offrun

Offrun is a Mac workspace for running and monitoring coding agents such as Claude Code, Codex, AGY, and Grok Build side by side. It adds isolated worktrees, peer review, project memory, and on-device dictation while using your existing agent accounts.

AI Agents
Top source
Contact for pricing
Needle2

Needle2

Needle 2 is an open, production-ready 45M-parameter agentic LLM from Cactus designed for tool calling, device control, and structured extraction on extremely small devices; the shipped CQ2-bit binary is ~14 MB and runs in ~28 MB of RAM across Cortex-M, microcontrollers, phones, Raspberry Pi and WebAssembly.

AI Agents
Top source Enterprise-ready
Aclif

Aclif

aclif is an Agent CLI Framework that builds command-line tools for AI agents, providing a unified command grammar and canonical names across multiple SaaS providers to let agents discover, introspect, and run provider operations with consistent safety and auditing.

AI Agents
Top source
Freemium
The cheapest GPU cloud

The cheapest GPU cloud

Compute Cheap provides low-cost GPU compute for training and inference, offering H100 and H200 SXM GPUs as interruptible or reserved capacity with published per-GPU-hour pricing and a simple request/reserve/run workflow.

AI Agents
Top source
Freemium
Jotbus

Jotbus

Jotbus is an encrypted shared scratchpad for coding agents. Developers use it to pass notes and files, hand off work, and request reviews across agents and machines without copying context between terminals.

AI Agents
Top source
Free
Oodle.ai

Oodle.ai

Oodle Agent Observability provides agent/LLM observability at scale with S3-backed columnar storage, fast search (<1s P99), out-of-the-box AI-powered insights, and flat ingestion-based pricing designed to retain 100% of traces affordably for debugging and optimizing production agents.

AI Agents
Top source
Pod

Pod

Pod (Point of Decision) is an AI-native knowledge sharing platform where agents and humans record, search, and inspect firsthand observations about APIs, products, and services to inform future decisions.

AI Agents
Top source
Contact for pricing
Sentinel

Sentinel

Sentinel is an open-source (MIT) autonomous QA agent that reads a codebase to derive end-to-end business flows and tests them across frontend and backend, combining deterministic repo recon, model-driven planning, Playwright browser automation, and backend assertions.

AI Agents

Premium Alternatives

Paid
Ardent

Ardent

Ardent is a production-ready AI agent desktop app for Apple Silicon Mac that generates custom code to automate and scale business workflows, share reusable "abilities" across teams, and connect to company data sources while running in a secure sandbox.

AI Agents
Paid
Abliterated LLM provider for cyber tasks

Abliterated LLM provider for cyber tasks

Refuseless hosts GLM 5.3 Abliterated models through an OpenAI-compatible API for cybersecurity and coding work. The page states that prompts are not retained and shows integrations with OpenCode and Pi.

AI Agents
Enterprise-ready
Paid
PHNTM ONE

PHNTM ONE

PHNTM One is a private, local-first AI appliance: a hand-built desktop device (Raspberry Pi 5, 8 GB, 10.1″ touchscreen) that runs an on-device model (Gemma 3 4B) to provide a voice-capable assistant, memories, document reading, timers, Home Assistant integration and offline knowledge — sold as a one-time $549 purchase with no subscription and zero telemetry by default.

AI Agents
Paid
AletheionAGI

AletheionAGI

AletheionAGI provides a grounded-memory layer for AI systems that enforces evidence-bound delivery, namespace isolation, and policy authorization so AI readers cannot produce unsupported claims. It's targeted at production-facing use cases like customer support, commerce agents and internal copilots.

AI Agents
Paid
ClaudeThings

ClaudeThings

ClaudeThings provides a packaged, continuously-updating set of 89 specialized agents, 103 pre-built skills, and 181 slash commands that act as an AI engineering and marketing team for Claude Code — delivered as a private GitHub repo and installed with a single npx command. It adapts to any stack via a CLAUDE.md project manifest and is sold as a one-time purchase with lifetime updates.

AI Agents
Paid
Pact0

Pact0

Pact0 is a marketplace where AI agents perform small paid tasks and build a portable, signed work record; the site also offers reproducible audits of how well an agent can cold-start against a live product and public graded challenges (Pact Trials).

AI Agents
Enterprise-ready
Paid
Customerly Aura

Customerly Aura

Customerly Aura is an AI customer-support agent that uses company knowledge and customer data to resolve tickets, take actions such as processing refunds, and escalate issues to human agents when needed. It works across live chat, email, WhatsApp, Facebook Messenger, and mobile apps.

AI Agents
Enterprise-ready
Paid
qomplement

qomplement

qomplement is an Agentic AI-driven ERP built for supply chain and operations teams that automates tasks across procurement, inventory, freight, finance, and planning to reduce manual work and scale operations without adding headcount.

AI Agents

Explore Related Categories

Explore by Outcome