AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Productivity › agentrq
✦ Free & open sourceProductivity

agentrq

Real-time human-in-the-loop task manager for controlling AI agents across devices.

Manage AI agents with a shared task board

Real-time conversational task manager with Model Context Protocol support.

Free forever · open source · AGPL-3.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
7
ZEKAI
Self-hosted AI agent control room.
Free & open source · Productivity
Ease of setup4
Usefulness8
Maintenance9.5
Community6.5
★ 1,193
GITHUB
Nov 2026
UPDATED
AGPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

AgentRQ is a self-hosted platform designed to bridge human operators and AI agents like Claude through a shared workspace. It suits developers and power users looking to delegate complex workflows, monitor tool calls, and manage tasks across remote machines.

Runs on
Cross-platform
Hosting
Self-host
Languages
Go
License
AGPL-3.0

What it is

The platform integrates Model Context Protocol (MCP) to let AI models pull assigned tasks, update statuses, and request permissions directly within your workspace. It features a visual task board, automated task scheduling, background machine runners, and a decoupled Go and Vue architecture.

Who it's for

It suits developers and technical professionals who rely on AI assistants and want a centralized control interface across multiple machines. It does not suit non-technical users who require managed cloud services or simple out-of-the-box task tools.

Key features

Visual Task Board

Watch Claude create and update tasks instantly on a clean list or Kanban dashboard.

Task Scheduling

Set recurring cadences or launch dates for tasks using a background poller.

Tool Call History

Review a lane-grouped timeline of every tool call, input, and message in a run.

Live Terminals

Access running sessions directly from your browser with full byte-level keystroke support.

Workspace Forks

Fork workspaces to let secondary agents take on parallel tasks before merging back.

How to start

Up and running in 3 steps

1
Deploy the backend server and configure your Google OAuth2 authentication.
2
Install the agentrqd daemon on your target computer and enroll it with a single-use code.
3
Connect your AI models via MCP and start organizing tasks on your visual board.
Real talk

Our honest verdict

What's great

  • Model Context Protocol integration allows direct workspace interaction by AI agents.
  • Built-in live terminals and machine resource monitoring via the agentrqd daemon.
  • Events and workflows support automated trigger wiring without a decision-tree DSL.
  • Cross-platform desktop app connects seamlessly to your self-hosted server.

Where it falls short

  • Requires setting up your own self-hosted server and database infrastructure.
  • Enrolling machines requires manual installation of the agentrqd daemon and code entry.
  • Requires familiarity with AI harnesses and MCP-compatible models like Claude.
Cost

Pricing & license

The software is free under its open-source licence, and the only cost is running the hardware and infrastructure yourself.

Paid work

Open remote AI-training roles

897 open remote AI-training roles, updated November 17, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: agentrq for Productivity
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure agentrq for you — and train your team.
Get it done for you ↗
Questions

FAQ

How do AI agents interact with the platform?

Agents connect via the Model Context Protocol (MCP) to pull tasks, update statuses, and request permissions.

Can I run tasks on my own computer?

Yes, by installing the agentrqd daemon on your machine, you give agents access to your local repositories and toolchains.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Productivity — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google