Quick setup instructions for DeerFlow.
DeerFlow uses a YAML configuration file that should be placed in the project root directory.
-
Navigate to project root:
cd /path/to/deer-flow -
Copy example configuration:
cp config.example.yaml config.yaml
-
Edit configuration:
# Option A: Set environment variables (recommended) export OPENAI_API_KEY="your-key-here" # Optional: pin the project root when running from another directory export DEER_FLOW_PROJECT_ROOT="/path/to/deer-flow" # Option B: Edit config.yaml directly vim config.yaml # or your preferred editor
-
Verify configuration:
cd backend python -c "from deerflow.config import get_app_config; print('✓ Config loaded:', get_app_config().models[0].name)"
- Location:
config.yamlshould be indeer-flow/(project root) - Git:
config.yamlis automatically ignored by git (contains secrets) - Runtime root: Set
DEER_FLOW_PROJECT_ROOTif DeerFlow may start from outside the project root - Runtime data: State defaults to
.deer-flowunder the project root; setDEER_FLOW_HOMEto move it - Skills: Skills default to
skills/under the project root; setDEER_FLOW_SKILLS_PATHorskills.pathto move them
The backend searches for config.yaml in this order:
- Explicit
config_pathargument from code DEER_FLOW_CONFIG_PATHenvironment variable (if set)config.yamlunderDEER_FLOW_PROJECT_ROOT, or the current working directory whenDEER_FLOW_PROJECT_ROOTis unset- Legacy backend/repository-root locations for monorepo compatibility
Recommended: Place config.yaml in project root (deer-flow/config.yaml).
If you plan to use Docker/Container-based sandbox (configured in config.yaml under sandbox.use: deerflow.community.aio_sandbox:AioSandboxProvider), it's highly recommended to pre-pull the container image:
# From project root
make setup-sandboxWhy pre-pull?
- The sandbox image (~500MB+) is pulled on first use, causing a long wait
- Pre-pulling provides clear progress indication
- Avoids confusion when first using the agent
If you skip this step, the image will be automatically pulled on first agent execution, which may take several minutes depending on your network speed.
# Check where the backend is looking
cd deer-flow/backend
python -c "from deerflow.config.app_config import AppConfig; print(AppConfig.resolve_config_path())"If it can't find the config:
- Ensure you've copied
config.example.yamltoconfig.yaml - Verify you're in the project root, or set
DEER_FLOW_PROJECT_ROOT - Check the file exists:
ls -la config.yaml
chmod 600 ../config.yaml # Protect sensitive configuration- Configuration Guide - Detailed configuration options
- Architecture Overview - System architecture