workflowintermediateOpenCLAW

Orchestrate a Multi-Agent Team with OpenCLAW and Shared Memory

This guide details how to build a coordinated team of specialized AI agents using the OpenCLAW framework. The agents collaborate by reading and writing to shared files, allowing them to work in parallel on complex tasks while being managed from a single Telegram chat group.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Set Up Workflow: Orchestrate a Multi-Agent Team with OpenCLAW and Shared Memory

## What This Is
This guide details how to build a coordinated team of specialized AI agents using the OpenCLAW framework. The agents collaborate by reading and writing to shared files, allowing them to work in parallel on complex tasks while being managed from a single Telegram chat group.

Source: https://sidsaladi.substack.com/p/openclaw-101-2026-march-29-the-complete

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)

Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?

## Source Access Note

The source URL (https://sidsaladi.substack.com/p/openclaw-101-2026-march-29-the-complete) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.

## What to Implement

This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.

- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files

## Additional Context

- Clone the 'awesome-openclaw-usecases' repository from GitHub user 'hesamsheikh' to access the multi-agent team configuration files and reference implementation.
- Create a `team/` directory in the user's project root. Inside it, create the shared memory files `GOALS.md`, `DECISIONS.md`, and `PROJECT_STATUS.md`, along with an `agents/` subdirectory for individual agent configurations.
- For each required agent role (e.g., milo, josh, dev), create a subdirectory in `team/agents/` and define its personality, responsibilities, and primary LLM in a `SOUL.md` file. Configure the master `AGENTS.md` file to map these agents to their Telegram handles for command routing.

## Reference Implementation

```
team/
├── GOALS.md
├── DECISIONS.md
├── PROJECT_STATUS.md
├── agents/
│   ├── milo/
│   ├── josh/
│   └── dev/
```

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

3,268 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Clone the 'awesome-openclaw-usecases' repository from GitHub user 'hesamsheikh' to access the multi-agent team configuration files and reference implementation.
02Create a `team/` directory in the user's project root. Inside it, create the shared memory files `GOALS.md`, `DECISIONS.md`, and `PROJECT_STATUS.md`, along with an `agents/` subdirectory for individual agent configurations.
03For each required agent role (e.g., milo, josh, dev), create a subdirectory in `team/agents/` and define its personality, responsibilities, and primary LLM in a `SOUL.md` file. Configure the master `AGENTS.md` file to map these agents to their Telegram handles for command routing.

CODE INTELLIGENCE

bash

team/
├── GOALS.md
├── DECISIONS.md
├── PROJECT_STATUS.md
├── agents/
│   ├── milo/
│   ├── josh/
│   └── dev/

FIELD OPERATIONS

Automated Content Generation Pipeline

Build a multi-agent team where a 'Researcher' agent scrapes sources for topics, a 'Writer' agent drafts articles, an 'Editor' agent refines the text, and a 'Publisher' agent posts the final content to a CMS. The team coordinates using a shared `CONTENT_PIPELINE.md` file for status tracking.

Autonomous DevOps Incident Response Team

Create an AI team where a 'Monitor' agent watches logs for errors, a 'Diagnoser' agent analyzes the errors and system state, and a 'Responder' agent attempts automated fixes like restarting a service. All actions and incident statuses are logged in a shared `INCIDENTS.md` file.

STRATEGIC APPLICATIONS

→A solo founder can deploy a team of AI agents for project management, market research, and code reviews, allowing them to focus on high-level strategy while the agents handle daily execution and reporting.
→A marketing agency can automate client content creation by assigning a research agent, a copywriting agent, and a social media agent who collaborate through a shared content calendar file, ensuring a consistent and efficient workflow.