I fixed OpenClaw so it actually works (full setup)

Описание: I sit down with Moritz Kremb, an OpenClaw power user and agency builder based in Berlin, to break down how to actually make OpenClaw useful. Moritz walks through a 10-step optimization guide covering everything from troubleshooting and memory management to model selection and security basics. He then demos two real systems he built with OpenClaw: a full short-form video content pipeline and a conversational CRM. This episode is for anyone who tried OpenClaw, hit a wall, and wants a clear path to turning it into a superhuman digital employee.

Timestamps
00:00 – Intro and episode promise
02:17 – What is OpenClaw
03:17 – OpenClaw vs. ChatGPT vs. Claude Code
07:43 – Where Claude Cowork and Dispatch fit in
09:47 – Why choose OpenClaw over Cowork
11:03 – Step 1: Setting up OpenClaw
14:46 – Step 2: Personalize your workspace files
18:04 – Step 3: Fix and optimize memory
22:43 – Step 4: Choose the right model (OAuth method)
25:56 – Anthropic ban and model provider gray areas
27:33 – Step 5: Organize Telegram groups and topics
30:19 – Step 6: Understand the three browser modes
35:18 – Step 7: Skills — built-in, marketplace, and custom
39:03 – Step 8: Optimize the heartbeat file
42:00 – Step 9: Security basics and prompt injection
48:08 – Step 10: Least access principle and agent-owned accounts
49:52 – Use case 1: No AI Slop content system
58:37 – Use case 2: Conversational CRM
01:01:15 – Final thoughts on the future of personal agents
01:02:55 – Jensen Huang's take: OpenClaw as the new computer

Key Points

Upload the OpenClaw documentation into a Claude project to create a dedicated troubleshooting baseline — it solves roughly 99% of setup issues.
Use the OAuth method (your existing $20 ChatGPT or Anthropic subscription) to avoid expensive API costs, and always configure backup models.
Memory problems are almost always caused by memory never being saved in the first place; add an auto-save instruction to the heartbeat file so it logs every 30 minutes.
Organize your OpenClaw conversations into separate Telegram groups and topics with group-specific system prompts to avoid context bleed.
Stronger models are meaningfully more resistant to prompt injection; pair that with least-access principles and agent-owned accounts for a solid security posture.
Custom skills are the path to real automation — whenever you do something repeatedly, tell your OpenClaw to turn it into a skill.

Numbered Section Summaries

1. OpenClaw Explained: What It Is and How It Differs

Moritz breaks down OpenClaw as the first truly personal, autonomous agent — one that remembers, runs on a heartbeat every 30 minutes, executes cron jobs, and lives inside whatever chat app you already use. He maps the evolution from ChatGPT (cloud chat) to Claude Code (local files) to OpenClaw (persistent, proactive, and portable).

2. OpenClaw vs. Claude Cowork and Dispatch

Anthropic's new Dispatch feature and Claude Cowork are moving toward what OpenClaw already does, but OpenClaw remains more powerful and feature-rich today. Moritz frames the long-term comparison as Linux vs. Windows: the open-source version attracts community contribution, flexibility, and customization that proprietary tools have a harder time matching.

3. The 10-Step Optimized Setup

The core of the episode. Moritz walks step by step through: creating a troubleshooting project with the official docs, personalizing workspace files (agents.md, soul.md, user.md, identity.md), fixing memory with compaction settings and heartbeat auto-save, selecting models via OAuth, organizing Telegram groups with system prompts, understanding the three browser modes, activating and building skills, tuning the heartbeat file, hardening security, and applying least-access principles with agent-owned accounts.

4. Model Selection and the OAuth Shortcut

Instead of paying per-API-call, Moritz recommends hooking OpenClaw into an existing $20 ChatGPT subscription via OAuth. He suggests setting up a backup chain — OpenAI as primary, Anthropic as secondary, and open-source models through OpenRouter or Kilo Gateway as fallbacks — so the agent always has a working brain.


The #1 tool to find startup ideas/trends - https://www.ideabrowser.com/

LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/

The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/

FIND ME ON SOCIAL
X/Twitter:   / gregisenberg  
Instagram:   / gregisenberg  
LinkedIn:   / gisenberg  

FIND MORITZ ON SOCIAL
X: https://x.com/moritzkremb
Youtube:    / @promptwarrior  
Instagram:    / @promptwarrior