OpenClaw Multi-Agent Collaboration: A Field Report on Pitfalls & Solutions 🦞
📋 Project Background
The goal was to build a collaborative system of four specialized AI assistants:
- Fugui (Coordinator): Overall orchestration and management.
- Code (Coder): Development and tool creation.
- Yamei (Analyst): Deep data analysis.
- Soros (Vision): Chart and image recognition.
However, the path to getting them working together was filled with unexpected bugs. Here is a实录 (field record) of the pitfalls we encountered and how we fixed them.
💥 The Pitfalls We Encountered
workspace directory, meaning they were all reading the exact same SOUL.md file.
@mention other bots in the group chat, they remained completely unresponsive.
- The
@sent by Fugui was plain text, not a valid Telegram mention entity. - Telegram Platform Limitation: Bots generally cannot see messages sent by other bots.
- Bots with Privacy Mode ENABLED only receive messages where they are explicitly mentioned by a human user.
agentToAgent configuration, but Fugui still couldn't invoke other agents.
agentToAgentis designed for a Single-Bot, Multi-Agent architecture.- We were running a Multi-Bot architecture (4 independent Telegram bots).
- Functions like
sessions_spawnorsessions_sendcannot cross bot boundaries.
groupPolicy: "allowlist", but new groups couldn't use the bots.
groupPolicy: "open" for flexibility!✅ The Final Working Solution
Architecture Design
⬇️
4 Agents + 4 Independent Workspaces
⬇️
Shared: knowledge_hub + memory + skills
Core Configuration Steps
1. Independent Workspaces (Critical!)
Each bot must have its own directory to maintain its unique identity (SOUL.md).
2. Shared Knowledge Base
To enable collaboration, create symbolic links (symlinks) to a central knowledge hub.
3. Privacy Mode Configuration
- Coordinator Bot (Fugui): Set to
DISABLED. It needs to see all messages to orchestrate. - Specialist Bots: Set to
ENABLED. They should only wake up when explicitly mentioned by a human.
New Collaboration Workflow
Instead of real-time bot-to-bot messaging (which doesn't work), we use Shared Knowledge Base Collaboration:
- Yamei (Analyst) → Analyzes data → Writes results to
fraud_detection/ - Code (Coder) → Develops tools → Saves scripts to
tools/ - Soros (Vision) → Recognizes charts → Saves insights to
visuals/ - Fugui (Coordinator) → Reads all folders → Synthesizes and reports to the user.
🎯 Best Practices Summary
✅ Keep Independent
workspace directories and SOUL.md files. This prevents identity confusion.
✅ Share Resources
knowledge_hub, memory, and skills. Use symlinks to connect them.
✅ Collaborate via Files
Rely on reading/writing to the shared knowledge base rather than trying to force real-time bot-to-bot calls.
🏁 Conclusion
The correct posture for a Multi-Bot OpenClaw architecture is simple:
- Give every bot its own independent workspace to avoid personality clashes.
- Enable collaboration through a shared knowledge base, bypassing Telegram's bot-messaging restrictions.
- Let each specialist do their job, save the results, and let the Coordinator aggregate the findings.
With this configuration, our four AI assistants now collaborate perfectly, with zero identity confusion!