Skip to content
中文

Basic Configuration

FinClaw's runtime configuration is centralized in the .env file in the deployment directory (generated from .env.example by init-env.sh).

Required Items

VariableDescriptionExample
LLM_PROVIDERLLM providerdeepseek
LLM_MODELModel namedeepseek-v4-flash
LLM_API_KEYAPI key(required)
LLM_BASE_URLCustom base URL (as needed)https://api.deepseek.com/v1

Common Optional Items

VariableDefaultDescription
ADMIN_EMAILSadmin@example.comAdministrator emails (comma-separated); determines admin privileges
AI_INFRA_RS_GLOBAL_CONCURRENCY64Global concurrency limit for the AI runtime
AI_INFRA_RS_PER_USER_CONCURRENCY10Per-user concurrency limit
AI_INFRA_RS_RPM_PER_USER120Per-user requests-per-minute limit

For more configuration, see Business Configuration and Operations Configuration.

Customizing the External Port

By default, FinClaw exposes the API Gateway on host port 26100 (the api-gateway service in docker-compose.yml maps 26100:26100). If that port is taken or your environment requires a different ops port, change it as follows (example: switch to 28100).

Using docker-compose.override.yml

Leaves the original docker-compose.yml untouched, so upgrades do not overwrite your change.

bash
cd /data/chatkit-offline-release-<version>-linux-amd64/deploy

cat > docker-compose.override.yml <<'EOF'
services:
  api-gateway:
    ports:
      - "28100:26100"   # left = host port, right = container port (DO NOT change)
EOF

# Restart to apply
./scripts/fleet.sh basic down
./scripts/fleet.sh basic up -d

Digital Ecosystem Infrastructure.