Vibe Coding Discoveragentrq
View on GitHubAgentRQ: 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.
AgentRQ is a self-hosted human-in-the-loop platform for supervising AI agents: agents see and update workspace tasks over MCP, while you approve tool calls, watch live terminals on enrolled machines, and trigger work via schedules, events and workflows.
Use Cases
Delegate tasks to AI coding agents and track them on a Kanban boardRun and watch Claude Code sessions on your own enrolled machinesGate sensitive agent tool calls behind human approvalSchedule recurring agent tasks that auto-spawn when dueChain workspaces via named events and workflow graphsAttach to agent sessions from a browser live terminalDrive AgentRQ tasks from a browser agent via WebMCPManage workspace tasks from the CLI alongside an agentSearch full tool-call and message trajectory of an agent runDictate task descriptions with on-device speech-to-textAuto-generate task titles locally with no API callSelf-host an agent-human collaboration server with OAuth2 and JWTExtend the desktop app with Node modules that call MCP toolsReview CPU/memory/disk before launching another agent on a box
Built With
- Language
- Go
- Frameworks
- Go · Fiber · GORM · SQLite · Vue 3 · Pinia · Tailwind CSS · Electron · Vite · Electron Builder · mcp-go · Docker
Tags
agent-supervision · human-in-the-loop · mcp-server · acp-gateway · task-management · self-hosted · claude-code · agent-orchestration · real-time · task-scheduler · kanban · live-terminals · desktop-app · workflow-graph · webmcp · multi-agent