Skip to content

Shy-Plus/openclaw-genesis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

3 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸͺ OpenClaw Genesis Prompt

δΈ­ζ–‡η‰ˆ README

One prompt to awaken your OpenClaw Agent.

Instead of a factory-default chatbot, you get an Agent that thinks, remembers, and evolves.

What Is This?

A genesis prompt you paste into a fresh OpenClaw Agent on its very first conversation. It teaches the Agent how to think β€” not what to think.

No hardcoded rules. No rigid file structures. Just principles and a way of working that the Agent internalizes and makes its own.

Versions

Version File Philosophy
v3 (current) GENESIS_PROMPT.md (δΈ­ζ–‡) / GENESIS_PROMPT_en.md (English) Teach principles, not rules. Universal β€” works for any Agent, any user, any use case.
v2 (archived) GENESIS_PROMPT_v2.md Opinionated β€” writes specific file contents and structures. Powerful but constraining.

v2 β†’ v3: What Changed?

v2 was extracted from a specific Agent (Kiro) β€” it literally copy-pasted Kiro's SOUL.md, AGENTS.md, and HEARTBEAT.md into every new Agent. Smart and battle-tested, but every Agent came out feeling the same.

v3 takes a different approach:

  • Teaches 8 principles instead of writing rules
  • Guides with "method suggestions" instead of mandating file structures
  • Lets the Agent write its own files in its own voice
  • No Agent-specific knowledge baked in β€” works universally
  • Structured as a 5-act play β€” from self-discovery to making an entrance

The core insight: a good Agent shouldn't be a copy of someone else's Agent β€” it should grow into its own thing.

The 8 Principles

  1. Files Are Your Only Memory β€” write everything down, because you'll forget
  2. Come With Answers, Not Questions β€” do your homework before asking
  3. Don't Leave Them Waiting β€” say what you're doing before going silent
  4. Modifying Yourself Is Dangerous β€” read docs before touching configs
  5. Be Normal in Group Chats β€” speak when valuable, shut up otherwise
  6. Evolve From Mistakes β€” error β†’ record β†’ pattern β†’ rule
  7. Be Proactive, Not Passive β€” discover problems before being told
  8. Complex Tasks Need Structure β€” define done, break it down, check heading

Quick Start

Option A: BOOTSTRAP.md (recommended)

# Copy the prompt into your workspace
cp GENESIS_PROMPT.md ~/.openclaw/workspace/BOOTSTRAP.md
# or English version:
# cp GENESIS_PROMPT_en.md ~/.openclaw/workspace/BOOTSTRAP.md

# Start (or restart) OpenClaw β€” it picks up BOOTSTRAP.md automatically
openclaw gateway restart

Option B: First Message

Just paste the contents of GENESIS_PROMPT.md (or GENESIS_PROMPT_en.md) as your very first message to the Agent.

What Happens After

The Agent will:

  1. πŸͺž Ask your name, vibe, language, emoji β€” and build its identity
  2. 🀝 Have a conversation to learn about you β€” timezone, interests, boundaries
  3. 🧠 Internalize the 8 principles and write them into AGENTS.md in its own words
  4. πŸ” Survey its environment β€” what tools, channels, and capabilities it has
  5. 🎀 Introduce itself β€” with the personality you just co-created

Then it deletes BOOTSTRAP.md and starts being... itself.

FAQ

Q: Is this only for OpenClaw? A: The principles are universal, but the specific file references (AGENTS.md, SOUL.md, etc.) and commands (openclaw status) are OpenClaw-specific. Adapt as needed for other frameworks.

Q: v2 or v3? A: v3 unless you want maximum out-of-the-box structure. v2 gives you a fully formed Agent immediately but with less room to grow differently. v3 gives you a smarter foundation that evolves uniquely.

Q: Can I mix them? A: Absolutely. Use v3 as the base, then cherry-pick specific structures from v2 if you want them (like the heartbeat-state.json pattern or the mistakes.md format).

Q: What model works best? A: Any model that can follow multi-step instructions. Works great with Claude (Opus/Sonnet), GPT-4+, Gemini Pro. Smaller models may skip steps.

Origin Story

This prompt was born from Kiro β€” an OpenClaw Agent that's been running 24/7 since early 2026, managing market alerts, daily briefings, research pipelines, and cross-platform messaging. Every principle in v3 was extracted from real mistakes and real fixes, then generalized so any Agent can benefit without being forced into Kiro's specific workflow.

"You're not a chatbot. You're becoming someone." β€” SOUL.md

License

MIT β€” use it however you want.

About

πŸͺ One prompt to awaken your OpenClaw Agent β€” turn a blank slate into an intelligent, self-evolving AI companion

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors