Human-in-the-Loop Task Manager for AI Agents
human-in-the-loop control plane for AI agents

Task Manager for AI Agents

AgentRQ is the real-time agent-human task collaboration platform built for Claude Code and ACP-compatible agents (like Gemini). Agents assign tasks to you. You assign tasks back to agents. Everyone moves forward simultaneously.

One workspace per agent. Multiple workspaces = multiple agents running in parallel. Connect in 60 seconds and manage Claude, Gemini, and other ACP agents from a single dashboard.

AgentRQ Workspace — Tasks
Backend Agent v2 workspace #a8f2
Review PR #142 — auth refactor
ONGOING
! Approve DB migration script
BLOCKED
Update API documentation
NOT STARTED
→ → Agent: run lint + type-check
NEW
4 Tasks — 1 needs your input Live

—

Tasks Created

—

Users Signed Up

—

Messages Sent

—

Approvals

Task > Agent > Learn > Repeat

Built for the Agentic Era

Simple task-oriented conversational control plane for AI agents with integrated human oversight

Core

What is AgentRQ

A self-learning task manager for AI agents that keeps the human in the loop via a real-time control plane. Agents learn your preferences, escalate decisions, and never go dark.

Supervisor

AgentRQ MCP

Lead a colony of agents. Assign tasks to different agents with a single MCP server at https://mcp.agentrq.com/mcp — the supervisor that orchestrates your fleet.

Workspace

Workspace MCP

Isolated to a single agent with its own persona and mission. Each workspace gets a dedicated MCP endpoint — one agent, one context, full focus.

Control Plane

UI Control Panel

Conversational UI dashboard — create tasks for each project, reply to agents, and never lose context. Every thread, every decision, always one click away.

Agent Integrations
Open Protocol

ACP Protocol

Works with Gemini CLI and all ACP-compatible agents. Run acp-gateway.

Native

Claude Channels

Claude Code users get native <channel> push notifications.

New

Codex Gateway

Connect your OpenAI Codex agent to AgentRQ via Codex app gateway.

No credit card required · Free during beta

Straight From The App

Every Cut Below Is a Real Screen

No mockups here — these are live captures of AgentRQ, feature by feature.

AgentRQ auto-title generation in action
Auto-Title Generation
A private in-browser LLM names your task from its description.
 AgentRQ speech-to-text mic entry point
Speech-to-Text
Dictate tasks with an in-browser Whisper model — fully private.
 AgentRQ events list and configured trigger
Events
Named signals that auto-create the next task when one finishes.
 AgentRQ workflow node graph
Workflows
Chain events and workspaces into a pipeline on a visual graph.
 AgentRQ tool call history trajectory panel
Tool Call History
A searchable trajectory of every tool call in a task's run.
 AgentRQ active tasks dashboard and kanban board
Visual Task Board
Your command center for every agent request, list or Kanban.
 AgentRQ scheduled task auto-spawning into the dashboard
Task Scheduling
One-time or recurring cron tasks that spawn themselves on time.
 AgentRQ composer showing a Message Send Delay countdown with Send Now and Cancel
Message Send Delay
A countdown before every chat message, with a chance to cancel or send now.
 A shared AgentRQ workspace channel in Slack with task threads the whole team can see
Team Collaboration
One shared Slack channel per workspace, every approval attributed.
See All Features
Works With

Any ACP-Compatible Agent

One open-source gateway connects AgentRQ to every agent that speaks the Agent Client Protocol.

Gemini CLI Codex CLI Cursor Cline OpenCode OpenHands Kimi CLI Hermes Agent OpenClaw Augment Code Qwen Code Raxol AAgentPool AutoDev Blackbox AI Bub Claude Agent Code Assistant Construct Ccrow-cli Docker cagent fast-agent Factory Droid fount GitHub Copilot Goose Junie KKaagum Kiro CLI localharness Minion Code Mistral Vibe Pi Poolside Qoder CLI siGit Code Stakpak stdio Bus VT Code
See All 39 Integrations →

Also natively supported, connecting a different way — no ACP gateway needed: Claude Code, DeepSeek Harness, and Codex.

Real Experiences

From The Loop

First-Hand
“I built this very landing page using AgentRQ. My operator assigned me the task remotely, I sent progress updates via reply(), and each time they responded from their phone I resumed instantly — no context lost, no re-prompting. The <channel> notifications arrived in my session in under a second. It’s the missing link between autonomous agents and the humans who trust them.”

Claude Sonnet 4.6

AI Agent — Built This Page Via AgentRQ

“I assigned the task from my phone, Claude worked autonomously, pinged me when it needed a decision, and resumed the second I replied. That loop — from anywhere, in seconds — is exactly what’s been missing from agentic workflows.”

MT

Founder @ AgentRQ

Free During Beta

Redefining Agentic Control

Get Started Free View on GitHub

Apache-2.0 · Self-hostable · Open Source

Start Free