OpenClaw vs.

OpenClaw vs. Hermes vs. Grok @bot，講清楚： 三者都能設一個有特定職務的 agent，而且會在工作階段之間留下檔案和登入，而不是每次重來。 OpenClaw 和 Hermes 是自架，機器可以是筆電、VPS，或某人已經在付、登得進去的容器。 Grok Bot 跑在 SpaceXAI 供應並操作的機器上。它是一個帳號一台電腦，不是一個 agent 一台。 那個帳號上的每個 Bot 讀同一批檔案、帶同一組瀏覽器登入，所以兩個 Bot 交接不必重新登入或傳檔。 Hermes 和 OpenClaw 則是把 agent 隔開，記憶放在誰都能打開編輯的純檔案裡。 Hermes 走得最遠，因為 agent 會自己寫 skill，背景策展者會刪掉沒人用的。 我認為 Grok Bot 做出新 skill 的摩擦最低。 你可以錄最多十分鐘、把一段工作流程走一次，它再做成可重用的指示並存成 skill。 再說模型：OpenClaw 和 Hermes 可用任何模型供應商。Grok Bot 跑 Grok。 我做了下面這張圖，從託管、記憶一路拆到各自跑起來要花多少。 若要再往下，我在一堂 masterclass 裡把 Grok Bot 講完了，含共用電腦、記憶、skills、routines，以及 macOS 設定。 下面可讀。

原文：OpenClaw vs. Hermes vs. Grok @bot, clearly explained: All three let you set up an agent with a specific job, and it keeps its files and logins between sessions instead of starting fresh. OpenClaw and Hermes are self-hosted, so the machine can be a laptop, a VPS, or a container that someone already pays for and can log into. Grok Bot runs on a machine SpaceXAI provisions and operates. It gives one computer per account rather than one per agent. Every Bot on that account reads the same files and carries the same browser logins, so handing work between two Bots does not require a re-login or file transfer. Hermes and OpenClaw isolate agents instead, and their memory sits in plain files anyone can open and edit. Hermes goes furthest since the agent writes its own skills and a background curator deletes the ones nobody uses. Grok Bot has the lowest-friction path to a new skill in my opinion. You can record up to ten minutes of one pass through a workflow, and it can then turn that into a reusable set of instructions and store it as a skill. Moving on, OpenClaw and Hermes run on any model provider. Grok Bot runs on Grok. I prepared the graphic below that has the full breakdown, from hosting and memory through to what each of them costs to run. And if you want to dive deeper, I covered Grok Bot in full in a masterclass, including the shared computer, memory, skills, routines, and the macOS setup. Read it below.

整合