Skip to main content

​
Quick Install

npx siclaw
That’s it. npx downloads and runs the latest version automatically.

​
Global Install

If you prefer a permanent installation: 
npm install -g siclaw
siclaw

​
From Source

git clone https://github.com/scitix/siclaw.git
cd siclaw
npm ci
npm run build
npm run dev

​
Configuration

Siclaw stores its configuration and data in ~/.siclaw/: 
~/.siclaw/
├── config/
│   └── settings.json     ← LLM provider, model, API key
├── data.sqlite            ← Session data (Gateway mode, sql.js)
├── memory/
│   ├── .memory.db         ← Investigation memory (node:sqlite)
│   └── *.md               ← Raw memory files
└── reports/
    └── deep-search-*.md   ← Investigation reports

​
LLM Configuration

Edit ~/.siclaw/config/settings.json (see settings.example.json for full format): 
{
  "providers": {
    "default": {
      "baseUrl": "https://api.anthropic.com/v1",
      "apiKey": "sk-ant-...",
      "api": "anthropic",
      "models": [{ "id": "claude-sonnet-4-20250514", "name": "Claude Sonnet 4" }]
    }
  }
}
Or use environment variable overrides: 
export SICLAW_LLM_API_KEY="sk-ant-..."
export SICLAW_LLM_BASE_URL="https://api.openai.com/v1"
export SICLAW_LLM_MODEL="gpt-4o"
See LLM Providers for Ollama, vLLM, and other setups.

​
Kubeconfig

Siclaw uses your default kubeconfig (~/.kube/config). To use a specific context: 
KUBECONFIG=/path/to/kubeconfig siclaw

​
Embedding (Optional)

To enable Investigation Memory with semantic search, add an embedding config: 
{
  "embedding": {
    "baseUrl": "https://api.example.com/v1",
    "apiKey": "sk-...",
    "model": "bge-m3",
    "dimensions": 1024
  }
}
Without embedding, memory features are disabled but all other functionality works normally.