Deployment Prerequisites
1. System Requirements
| Item | Requirement | Notes |
|---|---|---|
| OS | CentOS 8+ / RHEL 8+ / Ubuntu 22.04+ | ARM64 not supported; for Kylin / UOS evaluate against the matching RHEL/Ubuntu baseline |
| CPU architecture | x86_64 (amd64) | aarch64 not supported |
| Kernel | Linux 4.18+ | cgroup v2 and modern Docker required |
| CPU | 8 cores or more | 16 cores recommended for single-machine production |
| Memory | 16 GB or more | 32 GB recommended for single-machine production |
| Disk | 100 GB+ free | Data disk SSD recommended |
2. Software Dependencies
| Software | Version | Verify command |
|---|---|---|
| Docker Engine | 24.x or later | docker --version |
| Docker Compose | v2.x (not v1) | docker compose version |
| Base tools | tar, openssl | tar --version && openssl version |
3. Offline Package
| Item | Detail |
|---|---|
| Filename | chatkit-offline-release-1.0.xx-linux-amd64-xxxxxxxx.tar.gz |
| Size | ~ 4 GB |
| Contents | All microservice images + AI runtime (ai-infra-rs) + deployment scripts |
| Storage location | Data disk (e.g. /data/), not the system disk / |
4. LLM Runtime Credentials
FinClaw uses an external LLM provider for inference. Prepare the following environment variables before deployment:
| Variable | Description | Example |
|---|---|---|
LLM_PROVIDER | LLM provider | deepseek, openai |
LLM_MODEL | Model name | deepseek-chat, gpt-4o-mini |
LLM_API_KEY | API key | sk-xxxxxxxx... |
LLM_BASE_URL | Custom base URL (if needed) | https://api.deepseek.com/v1 |
5. Port Requirements
FinClaw uses ports in the 261xx ~ 264xx range by default, with the API Gateway (26100) as the external entrypoint.
| Purpose | Ports | External exposure |
|---|---|---|
| API Gateway (single entrypoint) | 26100 | ✅ Required |
| Other services | 261xx – 265xx | ❌ Internal |
See Deployment Components for the full port mapping.