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: