GitHub - guld/ROE.md: Your very own personal AI assistant born from a single Markdown file! Singularity, your way. Not just lobsters. 🦞

7 min read Original article β†—

ROE.md Logo

ROE.md - Raise Your Personal OpenClaw-like Creature From a Single Markdown File (alpha)

ROE.md is a single Markdown file to molt (raise) your own customized OpenClaw-like personal assistant into existence. Zero external dependencies! Except for the power of AI (cough)

Now call your favorite AI assistant to raise your highly personalized OpenClaw-like creature. What will you raise? A Lobster 🦞, an Octopus πŸ™ or something else?! 🐧 πŸ‘Ύ 🧞

Caution

Please note that ROE.md is still still in alpha stage, expect bugs, an unstable API and security issues!

How To Raise It

Remember, you can customize anything to your liking. Have fun~

Mini tutorial

We raise our own creature in this tutorial using an AI coding assistant (OpenCode, recommended) running on Arch, btw.

  1. Download or clone the ROE.md repository (e.g., ~/Downloads/ROE.md/).

  2. Open a directory in your terminal/powershell where you want the build to take place (e.g., ~/Work/projects on Unix/Mac or ~\Documents\projects on Windows)

  3. Start your favorite AI coding assistant, such as OpenCode, Claude Code, or OpenAI's Codex. (We use OpenCode in this example)

    # 1. Create a roe-agent directory, and move into it.
    # 2. Copy ROE.md from e.g., Downloads into the 
    #    roe-agent directory.
    # 3. Start OpenCode, Claude Code, OpenAI Codex or similar assistant.
    # Unix/Linux/Mac console
    
    mkdir roe-agent && cd $_ && cp ~/Downloads/ROE.md/ROE.md ROE.md
    
    # Now start the assistant
    opencode 
    # Windows Powershell
    
    mkdir roe-agent; cd roe-agent; Copy-Item ~\Downloads\ROE.md\ROE.md ROE.md
    
    # then start opencode
    opencode
  4. Let the AI assistant help you raise ROE.md by typing:

    Help me raise my personal agent by following the parenting steps in `./ROE.md` file exactly. Please ask clarifying questions before you start building.
    

    into the assistant's chat window.

  5. Your AI assistant should now read the ROE.md file and ask you to answer some initial questions, such as

    • which programming language to use,
    • which model provider your creature should connect to initially,
    • and if your creature should be based on the OpenClaw templates.
  6. We answer with something along those lines:

    Python, LM Studio API openai/gpt-oss-20b, CLI, yes
    

    Replace with your favorite programming language, provider and model of choice. Note: Some AI assistants may even provide you with a CLI to select these options.

    [!TIP] You can find a list of tested models and languages in the tests and benchmarks section further down.

  7. You may have to fix some initial bugs together with your AI coding assistant (e.g., OpenCode) depending on your choice of programming language, connector and template usage.

Once Your Agent Is Ready

Adapt to the programming language you selected during creation.

Suppose you selected Python as your programming language.

Test your agent by running python run_agent.py in a terminal/powershell.

If you selected to keep the OpenClaw-like agent templates the agent should should respond as follows on the first startup.

Hey. I just came online. Who am I? Who are you?

Once you answer these, test the agent's memory, tool calling and skills.

If you run into any bugs or errors, ask the AI coding assistant (e.g., OpenCode) to fix them.

If everything works as expected, great you are done and your personal AI assistant is ready!

If you like to share your personal agent with the community or you experimented on how to improve the ROE.md file and want to share your results, please read how to contribute.

Features (Pre-Release)

Caution

This project is pre-release. Features marked as β€œIn Development” work on main but may change. Planned features may depend on user feedback or evolving priorities.

Features that should work out of the box, once your agent is created.

Features Lifecycle Availability Note
CLI 🟑 In Development βœ… Works today integrated
GMail ⬜ Planned β€” via Skill, planned
Signal ⬜ Planned β€” via Skill, planned
Telegram 🟑 In Development βœ… Works today Plugin
Whatsapp ⬜ Planned β€” via Skill, planned
secret ⬜ Planned β€” secret, planned

Chat Multimedia Capabilities

Capability Lifecycle Availability Note
Documents ⬜ Planned β€” PDF, CSV ingestion
Image (OCR) 🟑 In Development βœ… Works today Depends on a model that provides vision capabilities
Voice (STT) 🟑 In Development βœ… Works today Depends on Voxtype + FFMPEG (API may change)
Voice (TTS) ⬜ Planned β€” β€”

Integrated Provider APIs

Provider Lifecycle Availability Note
Anthropic 🟑 In Development βœ… Works today Partial
llama.cpp ⬜ Planned β€” Depends on community feedback
LM Studio 🟑 In Development βœ… Works today Partial
OpenAI 🟑 In Development βœ… Works today Partial
Ollama ❓ Under review β€” No commitment yet

OpenClaw-style templates

ROE.md supports standard OpenClaw-style templates, and you’re welcome to bring your own as well.

Templates From Availability
AGENTS.md 🟑 In Development βœ… Works today
BOOTSTRAP.md 🟑 In Development βœ… Works today
HEARTBEAT.md 🟑 In Development βœ… Works today
IDENTITY.md 🟑 In Development βœ… Works today
MEMORY.md 🟑 In Development βœ… Works today
SKILLS.md 🟑 In Development βœ… Works today
SOUL.md 🟑 In Development βœ… Works today
TOOLS.md 🟑 In Development βœ… Works today
USER.md 🟑 In Development βœ… Works today

For AI model compatability refer to the tests and benchmarks section.

Tests And Benchmarks?

We test how some AI assistants perform at raising our custom agent executable from various ROE.md versions. The goal is to build an agent in less than 5 prompts.

Caution

Please note: Just because the agent builds and works, does not mean that it is secure and for example, cannot wipe your entire system! Be careful out there.

OpenCode:

Language AI Assistant Provider Builds in >5 Prompts, >100k Context Kimi-2.5 OpenAI Anthropic Z.ai MinMax2.5
Bash/shell Opencode OpenCode Zen ❌ ❌ ⬜ ⬜ ⬜ ⬜
Go Opencode OpenCode Zen ❌ ❌ ⬜ ⬜ ⬜ ⬜
JavaScript Opencode OpenCode Zen ❌ ❌ ⬜ ⬜ ⬜ ⬜
Python Opencode OpenCode Zen βœ… βœ… βœ… ⬜ ⬜ ⬜
↳ Codex OpenAI βœ… βœ… βœ… ⬜ ⬜ βœ…
Ruby Opencode OpenCode Zen ❌ ❌ ⬜ ⬜ ⬜ ⬜
Rust Opencode OpenCode Zen ⬜ ⬜ ⬜ ⬜ ⬜ ⬜
Zig Opencode OpenCode Zen ⬜ ⬜ ⬜ ⬜ ⬜ ⬜

Legend: Untested ⬜, Build failed ❌, Build passed βœ…, Under active development 🚧

We also test recent "cheap" local models as our goal is to give everyone a chance to build their custom personal agent. Here we increase the max prompts allowed to 10 to call it a success, because these models are not as smart as the current ones.

Local AI Assistants:

Language AI Assistant Provider Builds in >10 Prompts, >100k Context GPT-OSS-20b GLM-4.7 Qwen3.5-35b-a3b
Python OpenCode LM Studio 🚧 ⬜ ❌ ⬜

Legend: Untested ⬜, Build failed ❌, Build passed βœ…, Under active development 🚧

More tests comming soon.

Tip

Please help by running tests with various models yourself and contribute your results by opening an issue.

Contribute

Become part of the sponge by creating your own custom sponge/ROE-<username>-<version>.md file and make a pull request. Test ROE.md with your favorite programming language. Or help us out to improve the core ROE.md so that everyone can raise their personal agent.

Check out our contributing guide.

ROE.md was created initially by guld for raising his own custom OpenClaw-like personal agent from scratch. Based on a simple thought:

If AI assistants really can do everything? Why not create a personal AI assistant "from scratch", or at least from a single Markdown file?

-- guld 06 Feb 2026

Community

Read how to contribute and how to submit PRs. Well tested AI/vibe-coded PRs welcome!

A big hug and thanks to all contributors:

guld