Openclaw Dual Agent

name: openclaw-dual-agent description: "Run two OpenClaw agents simultaneously — a paid Anthropic agent and a free agent using either OpenRouter (cloud) or local Ollama models. Note: Ollama example defaults to hybrid setup with OpenRouter fallback — remove fallback/heartbeat refs for fully offline operation. Trigger phrases: multi-agent setup, add a second agent, free agent openclaw, run two agents, openrouter openclaw, ollama agent, local model openclaw, parallel agents, cost optimization agent." metadata: {"clawdbot": {"emoji": "🤖", "requires": {"bins": ["jq"]}, "env": ["ANTHROPIC_API_KEY"], "os": ["darwin", "linux", "win32"]}, "homepage": "https://clawhub.com/djc00p/openclaw-dual-agent"}

Multi-Agent OpenClaw Setup

Run a paid Anthropic agent and free OpenRouter agent side by side with separate Telegram bots.

Quick Start

1. Create two Telegram bots via @BotFather and extract chat IDs:

   curl https://api.telegram.org/bot{TOKEN}/getUpdates | jq '.result[0].message.chat.id'
   

2. Authenticate agents:

   # Run interactively — avoids exposing keys in shell history
   openclaw onboard
   

   ⚠️ Never pass API keys directly on the CLI (e.g. --anthropic-api-key ...) — it exposes them in shell history. Always use openclaw onboard interactively. Credential files (auth-profiles.json, openclaw.json) should be chmod 600.

3. Configure openclaw.json with two agents, separate bindings, and Telegram accounts.

4. Verify setup:

   openclaw doctor
   openclaw sessions cleanup \
     --store /Users/YOUR_USERNAME/.openclaw/agents/main/store \
     --enforce --fix-missing
   openclaw restart
   

Key Concepts

• Agent isolation: Each agent has its own agentDir, workspace, and model config.
• Binding routing: accountId in bindings directs Telegram messages to the correct agent.
• Model refs: Use provider/modelid format (e.g., anthropic/claude-sonnet-4-6).
• Per-agent auth: OpenRouter requires auth-profiles.json in each agent's directory.

Common Usage

Adding a free agent:

• Create agentDir at /Users/YOUR_USERNAME/.openclaw/agents/free-agent/agent
• Add agent entry to openclaw.json with model.primary: "openrouter/..."
• Create auth-profiles.json with OpenRouter API key in agent's directory
• Add binding with unique accountId (e.g., "tg2")
• Restart: openclaw restart

Switching models: Edit openclaw.json agent's model.primary and fallbacks with valid provider/id strings.

Masking secrets for logs:

cat ~/.openclaw/openclaw.json | \
  jq '.channels.telegram.accounts |= map_values(.botToken = "[REDACTED]")'

Option B: Local Ollama Agent (Free + Hybrid)

Instead of OpenRouter, run your second agent on a local Ollama model — free, private, and locally-hosted. The default config uses a hybrid approach with OpenRouter cloud fallback for reliability. For fully offline operation, see "Fully Offline Config" below.

Install & Configure Ollama

macOS:

# Install via Homebrew
brew install ollama

# Or download from https://ollama.ai

Start Ollama:

# In a dedicated terminal, keep it running
ollama serve

Pull a model (choose one based on your needs):

# Google Gemma 4 26B — good balance of capability and speed (17GB)
ollama pull gemma4:26b

# Meta Llama 3.3 70B — very capable, excellent reasoning (43GB)
ollama pull llama3.3:70b

# Qwen 2.5 32B — strong coding and multilingual (20GB)
ollama pull qwen2.5:32b

# Mistral 7B — fast and lightweight, good for quick responses (4GB)
ollama pull mistral:7b

Configure OpenClaw with Ollama Agent

Add the agent entry to openclaw.json (e.g., id: "ayo"):

{
  "id": "ayo",
  "name": "Ayo",
  "workspace": "/Users/YOUR_USERNAME/.openclaw/workspace-ayo",
  "agentDir": "/Users/YOUR_USERNAME/.openclaw/agents/ayo/agent",
  "model": {
    "primary": "ollama/gemma4:26b",
    "fallbacks": [
      "openrouter/free"
    ]
  },
  "heartbeat": {
    "every": "1h",
    "model": "openrouter/free"
  }
}

Key points:

• Model format: Always use ollama/modelname:tag (e.g., ollama/gemma4:26b, ollama/llama3.3:70b)
• No API key needed for Ollama: Ollama runs entirely locally. No auth-profiles.json required.
• Ollama must be running: Start ollama serve in a terminal before the gateway starts
• Pull first: Run ollama pull modelname:tag before configuring (the model must exist locally)
• ⚠️ Hybrid setup: The default example uses openrouter/free for fallback and heartbeat — this means prompts and context MAY route to OpenRouter cloud. See below for fully offline config.
• Add Telegram binding: Include a separate binding with a unique accountId (e.g., "tg_ollama") to route messages to Ayo

Fully Offline Config (No Cloud Routing)

If you want a truly local, offline-only Ollama agent with no external provider calls:

{
  "id": "ayo",
  "name": "Ayo",
  "workspace": "/Users/YOUR_USERNAME/.openclaw/workspace-ayo",
  "agentDir": "/Users/YOUR_USERNAME/.openclaw/agents/ayo/agent",
  "model": {
    "primary": "ollama/gemma4:26b",
    "fallbacks": []
  },
  "heartbeat": {
    "every": "1h",
    "model": "ollama/gemma4:26b"
  }
}

This config uses ONLY local Ollama models — no cloud provider traffic for primary, fallback, or heartbeat.

After config change:

# Verify no errors
openclaw doctor

# Restart the gateway
openclaw gateway restart

Common Gotchas

If you see "Invalid input" errors in openclaw doctor, check the model.primary format — it must start with ollama/.

References

• references/config-reference.md — Full openclaw.json, bindings, and auth-profiles.json examples
• references/troubleshooting.md — Common errors, fixes, and Node.js compatibility notes