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. observed · 2026-09-03
Health v2 · maintenance only
82/100
- Activity 100
- Release rhythm 100
- Longevity 11
Flags: young
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: 0.0
- age_days: 162
- days_rel: 0
- days_push: 0
- n_releases_24m: 5
Adoption not part of the score
1101 stars · 78 forks observed · 2026-09-03
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded
AgentRQ is a self-hosted, human-in-the-loop task management and collaboration platform for AI agents, built around the Model Context Protocol (MCP) and the Agent Client Protocol (ACP). It provides a real-time web dashboard with task boards, scheduling, events, and visual workflows so humans can assign, approve, and converse with agents like Claude Code, Gemini CLI, and Codex from any device.
Use cases
- manage claude code tasks from my phone
- human approval for ai agent actions
- schedule recurring tasks for ai agents
- chain multiple ai agents together with events
- self-hosted task manager for ai agents
- connect gemini cli to a task dashboard
- supervise multiple ai agents in parallel
When to choose
- you run autonomous coding agents (Claude Code, Gemini CLI, Codex) and need human oversight and approvals
- you want a self-hosted control plane with real-time task boards, scheduling, and event-driven agent workflows
- you need to manage multiple agents across mobile, web, and desktop with MCP/ACP integration
When to avoid
- you need a general-purpose project management tool without AI agent integration
- you want a fully autonomous orchestrator with no human-in-the-loop step
- you require a managed SaaS with enterprise compliance certifications rather than self-hosting
Facets
application · maturity active
agent-framework mcp workflow-automation scheduling chat-interface webhook large-language-models developer-tools self-hosted self-hosted cross-platform go browser human-in-the-loop mcp-server acp-gateway claude-code kanban task-scheduling agent-orchestration real-time sse gemini-cli codex task-manager ai-agents automation web-server docker mobile desktop
10 sources
- readme: https://github.com/agentrq/agentrq · fetched 2026-09-03 · 938b61d034a2
- homepage: https://agentrq.com · fetched 2026-08-29 · 9b6de62bb8d9
- site_page: https://agentrq.com/features · fetched 2026-08-29 · 445ee87c0ec0
- site_page: https://agentrq.com/docs · fetched 2026-08-29 · b8ef37739076
- site_page: https://agentrq.com/docs/connect-acp-agent · fetched 2026-08-29 · 4af53e1dc73d
- site_page: https://agentrq.com/docs/connect-claude-code · fetched 2026-08-29 · 243e98cbf826
- site_page: https://agentrq.com/docs/connect-codex-gateway · fetched 2026-08-29 · da2419830c2f
- site_page: https://agentrq.com/features/auto-title-generation · fetched 2026-08-29 · 3b3a393b5e97
- site_page: https://agentrq.com/features/speech-to-text · fetched 2026-08-29 · 26697ea0a512
- site_page: https://agentrq.com/features/events · fetched 2026-08-29 · d0d18ddca815
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| agentrq/agentrq | main | 82 |
For agents
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem