I am building Clawke, an open-source native workspace for managing AI agents like OpenClaw, Hermes, and Nanobot.
The problem I am trying to solve: AI agents are becoming more than chatbots. They ask for approvals, call tools, manage tasks, use skills, return files, and expose runtime status. A plain chat or IM-style interface gets awkward quickly.
Hey Product Hunt,
I built Clawke, an open-source AI agent workspace with native support for OpenClaw, Hermes, Nanobot, and more.
Most agent tools still feel like terminal sessions or regular chat apps. That works for simple text, but it breaks down when agents ask for approvals, run tools, manage tasks, expose skills, or need structured controls.
Clawke is built as a native management space for AI agents. It provides native OpenClaw / Hermes / Nanobot support, richer interaction surfaces for tool calls, approvals, tasks, skills, media, and gateway status, and clients across iOS, Android, macOS, Windows, and Linux.
Because agent workflows are handled natively, Clawke is more specialized and professional for managing AI agents than a regular chat or IM app.
I would love feedback from people building or using agents: which native interactions should an AI agent workspace handle better?
Links:
GitHub: https://github.com/clawke/clawke
iOS: https://apps.apple.com/us/app/cl...