agentrq/agentrq

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.

What it solves

AgentRQ provides a shared workspace for human-AI collaboration, solving the problem of fragmented task management when working with AI agents. It allows humans to delegate tasks to agents and track their progress in real-time through a visual interface, rather than relying solely on chat logs.

How it works

The platform uses the Model Context Protocol (MCP) to connect AI models (like Claude) to a task management system. It consists of a Go-based backend that manages workspaces and tasks, a Vue.js frontend for visualization, and a daemon (agentrqd) that can be installed on remote machines to allow agents to execute code and access toolchains directly in a user's environment.

Who it’s for

It is designed for developers and teams who use AI agents for software development and task automation and want a structured way to manage, schedule, and monitor their agentic workflows.

Highlights

  • Visual Task Board: A Kanban or list view of all tasks created or updated by AI agents.
  • Task Scheduling & Events: Ability to spawn tasks on a recurring cadence or trigger new tasks based on named signals (events).
  • Workflows: A visual graph for arranging events and workspaces to define release processes.
  • Remote Machine Execution: Enrolled machines allow agents to run in specific repositories with live terminal access for the human operator.
  • Skills: Importable playbooks (SKILL.md) that provide agents with standardized instructions and teams' best practices.
  • Workspace Forks: Ability to fork a workspace to run multiple agents in parallel on different tasks before merging results back.
  • On-Device AI: Browser-cached models for auto-title generation and Whisper-based speech-to-text transcription.

Related

  • Project
    agentconnect-md/agentconnect

    AgentConnect is an open‑source, self‑hosted platform that lets teams run many AI agents (Claude Code, OpenAI Codex, Grok Build, etc.) inside Slack, Discord, Telegram, Google Chat, GitHub, GitLab, Linear and other tools. Agents can call each other, keep memory, be routed by Jev, and act on webhooks or schedules. The system consists of Daemons (run agents), an optional Relay, and a Control‑Plane UI for config, auth and observability. It ships via Docker‑Compose for local use and a Helm chart for Kubernetes, all under Apache‑2.0.

  • Project
    SalesforceAIResearch/MCP-Universe

    An ecosystem for building and evaluating AI agents using the Model Context Protocol (MCP), featuring real-world benchmarks and tools for token cost reduction.

  • Project
    zereight/gitlab-mcp

    GitLab MCP Server is a lightweight, install‑once binary that exposes GitLab’s API as 275 MCP‑compatible tools (issues, merge‑requests, pipelines, wiki, releases, etc.) for AI agents. It supports PAT or OAuth authentication, multiple transports (stdio, SSE, streamable HTTP), fine‑grained permission modes, and can run locally, in Docker, or on custom GitLab instances. Designed for Claude, Codex, Cursor, VS Code, Copilot and other MCP clients, it lets LLM‑driven workflows manage GitLab resources without writing custom code.

  • Project
    Get-Concord-AI/concord-mcp

    Concord MCP is an open‑source, local‑first coordination layer that lets multiple AI coding assistants (Claude Code, Codex, Cursor, Gemini CLI, Grok Build, Goose, GitHub Copilot CLI, etc.) share a common work‑state. It provides a tiny MCP server backed by SQLite, a set of tools (`start_work`, `inspect_work`, `update_work`, `transfer_work`, `finish_work`) and a CLI (`concord status`, `dashboard`, `check`, …) so agents can claim files, detect overlaps before editing, exchange prompts/replies, hand off tasks, and generate review packets. Setup is a single `npm install -g @concord-ai/concord-mcp && concord setup`. The project is MIT‑licensed and sends optional anonymous telemetry.

  • Project
    IvanMurzak/Unity-MCP

    Unity‑MCP is a Unity package that connects LLM agents (Claude, Codex, etc.) to the Unity Editor and to compiled games. It provides 70+ built‑in “tools” (asset management, scene manipulation, scripting, testing, profiling, etc.) that the AI can call, enabling natural‑language creation, debugging, and runtime AI behaviour. Install via a UnityPackage, OpenUPM, or the `unity-mcp-cli`; configure an agent, auto‑generate a skill set, and start issuing commands like “create three cubes in a circle”. Extensible with optional skill packs for Animation, Cinemachine, Navigation, and more. MIT‑licensed.