deerflow（deerflow 搜索）

DeerFlow Integration

What This Skill Does

DeerFlow is a LangGraph-based deep research engine that chains web search, reasoning, and synthesis into structured reports. This skill provides OpenClaw integration for submitting and monitoring research tasks against a running DeerFlow API.

Runtime contract: The skill itself runs entirely locally (python3 only) and communicates with DeerFlow over HTTP. It does not install or run any external Docker images — those are operated independently by the user as the DeerFlow host.

This skill does NOT install DeerFlow or manage its services. It assumes a DeerFlow instance is already running and reachable.

Prerequisites

⚠️ External dependency — your DeerFlow host. DeerFlow itself runs as a separate service on your infrastructure (or a VPS). Its Docker images are maintained by the bytedance/deer-flow project. Review their security posture before deployment.

Required at runtime

Required only for initial DeerFlow deployment (one-time setup)

If DeerFlow is already running somewhere (yours, a colleague's, or a cloud instance), skip straight to Quick Start — no git/docker needed.

Deploying DeerFlow (if you don't have one)

🔴 Security note: The following steps pull Docker images and run services from the bytedance/deer-flow GitHub repository. You are responsible for reviewing those images and configurations before running them in your environment.

1. Clone and configure

git clone https://github.com/bytedance/deer-flow.git
cd deer-flow
cp .env.example .env

Edit .env with your model API keys:

# Required: at least one LLM provider
OPENAI_API_KEY=sk-...
# Or MiniMax
MINIMAX_API_KEY=...
MINIMAX_API_BASE=https://api.minimax.com

# Optional: Tavily for web search
TAVILY_API_KEY=tvly-...

2. Start API-only services

# No nginx, no frontend — just gateway + langgraph
docker compose up -d deer-flow-gateway deer-flow-langgraph

Verify:

curl http://localhost:2024/openapi.json | head   # should return OpenAPI spec
curl http://localhost:8001/health               # should return 200

3. Test with a manual task

curl -X POST http://localhost:2024/threads \
  -H "Content-Type: application/json" \
  -d '{}'
# Returns: { "thread_id": "..." }

Then submit a task:

curl -X POST http://localhost:2024/threads/{thread_id}/runs \
  -H "Content-Type: application/json" \
  -d '{
    "assistant_id": "lead_agent",
    "input": {
      "messages": [{
        "type": "human",
        "content": [{ "type": "text", "text": "Your research query here" }]
      }]
    },
    "config": {
      "recursion_limit": 200,
      "configurable": {
        "model_name": "minimax-m2.7",
        "thinking_enabled": true,
        "is_plan_mode": false,
        "subagent_enabled": false
      }
    }
  }'
# Returns: { "run_id": "..." }

Poll for completion:

curl http://localhost:2024/threads/{thread_id}/runs/{run_id}

When status = success, fetch results:

curl http://localhost:2024/threads/{thread_id}/history

Quick Start

/deerflow <research topic>

Example: /deerflow Analyze the Chinese AI companion market

The skill returns a thread_id and run_id for status tracking.

Architecture

This skill targets the minimal API-only DeerFlow deployment. Only two services are relevant to this skill:

Model Configuration

Set model_name in the configurable block:

Set thinking_enabled: true to enable extended chain-of-thought reasoning (recommended for research tasks).

Skill Scripts

This skill includes two helper scripts in scripts/:

submit_task.py

cd ~/.openclaw/workspace/skills/deerflow
python3 scripts/submit_task.py "Your research topic"
# Returns thread_id and run_id

check_status.py

python3 scripts/check_status.py <thread_id> <run_id>
# Polls until completion, then prints the full report

OpenClaw Tool Injection

The skill is auto-injected into OpenClaw as the deerflow tool. OpenClaw agents call it directly when the user triggers the keyword.

Resource Comparison

Troubleshooting

LangGraph returns 404

Verify the container is healthy:

docker ps | grep langgraph
curl http://localhost:2024/openapi.json

Task hangs or returns "error" status

Check LangGraph logs:

docker logs deer-flow-langgraph --tail 50

Model API errors

Ensure credentials in DeerFlow's .env are valid and the model_name in your request matches a configured provider.

File Structure

skills/deerflow/
├── SKILL.md           # This file
└── scripts/
    ├── submit_task.py  # Submit a research task
    └── check_status.py # Poll and retrieve results