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. Des…

LLM Mart 0 views 5 listing impressions
Transport
Not stated
Package
Registry id

No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.

AgentRQ is a real-time agent-human task collaboration platform built for Claude Code and ACP-compatible agents. It allows agents to assign tasks to users and users to assign tasks back, enabling simultaneous progress. The platform provides a conversational UI dashboard to create tasks and reply to agents.

AgentRQ supports 55 ACP-compatible agents via its ACP gateway. Claude Code users receive native push notifications through the platform. AgentRQ is open source under the Apache-2.0 license and self-hostable.

The software is free during beta with no credit card required. Users can run agents on their own computers and watch the terminal from anywhere.

Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.

Related servers

Fetch Official

Fetch a web page and hand the agent readable text instead of raw HTML.

stdio mcp-server-fetch
27 views
Filesystem Official

Give an agent scoped read and write access to directories you choose.

stdio @modelcontextprotocol/server-filesystem
24 views
Git Official

Read repository history, diffs and branches as tools an agent can call.

stdio mcp-server-git
23 views

Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.

21 views