by scitix
AI-powered SRE platform — read-only infrastructure diagnostics with deep investigation, security governance, and team collaboration
# Add to your Claude Code skills
git clone https://github.com/scitix/siclawRead-only investigation copilot for SRE teams
Website | Documentation | Slack
Siclaw is an open-source AI agent for DevOps and SRE teams. It is built for read-only infrastructure diagnostics: gather evidence, form hypotheses, validate them, and return a clear root-cause analysis without changing your environment directly. Describe a problem in plain language and Siclaw investigates it from the terminal, the web UI, or your team's chat channels.
No comments yet. Be the first to share your thoughts!
Three deployment modes share one agent core: TUI (single-user terminal), Local Server (Gateway + SQLite, multi-user), Kubernetes (isolated AgentBox pod per user). The Knowledge System feeds the agent with accumulated investigation experience (IM Phase 0–1 ✓) and team-wide knowledge via Qdrant (KR0 — in progress).
Siclaw supports three deployment profiles. For local usage, start from a dedicated working directory because Siclaw stores most runtime data in .siclaw/ relative to where you launch it.
mkdir -p ~/siclaw-work
cd ~/siclaw-work
Run the agent directly in your terminal. No server, no database. All operations are read-only by default — safe to run on your workstation.
# Install globally
npm install -g siclaw
# Run (interactive — prompts for LLM provider on first launch)
siclaw
# Single-shot
siclaw --prompt "Why is pod nginx-abc in CrashLoopBackOff?"
# Continue last session
siclaw --continue
git clone https://github.com/scitix/siclaw.git && cd siclaw
npm ci && npm run build:web && npm run build
npm link # register `siclaw` command globally
siclaw # TUI mode
siclaw --prompt "..." # single-shot mode
# Uninstall: npm unlink siclaw -g
Tip: Any OpenAI-compatible endpoint works — swap
baseUrlfor DeepSeek, Qwen, Kimi, or a local Ollama server.
A lightweight web UI backed by SQLite. No MySQL, no Docker required.
npm install -g siclaw
# Start the server
siclaw local
# Open http://localhost:3000
# Login: admin / admin (default credentials)
# Configure providers in Models
# Import kubeconfigs in Credentials
git clone https://github.com/scitix/siclaw.git && cd siclaw
npm ci && npm run build:web && npm run build
npm link # register `siclaw` command globally
siclaw local # start local server
# Uninstall: npm unlink siclaw -g
On first startup, Siclaw creates a local admin account:
adminadminSet SICLAW_ADMIN_PASSWORD before first launch if you want a different bootstrap password.
Production deployment uses Helm plus three container images: gateway, agentbox, and cron.
Build and push images if you are using your own registry:
make docker REGISTRY=registry.example.com/myteam TAG=latest
make push REGISTRY=registry.example.com/myteam TAG=latest
Then deploy the chart with a MySQL URL:
helm upgrade --install siclaw ./helm/siclaw \
--namespace siclaw \
--create-namespace \
--set image.registry=registry.example.com/myteam \
--set image.tag=latest \
--set database.url="mysql://user:pass@host:3306/siclaw"
The default chart exposes the Gateway Service on service port 80 and NodePort 31000.
.siclaw/config/settings.json/setup~/.siclaw/reports/Minimal example:
{
"providers": {
"default": {
"baseUrl": "https://api.openai.com/v1",
"apiKey": "sk-YOUR-KEY",
"api": "openai-completions",
"models": [{ "id": "gpt-4o", "name": "GPT-4o" }]
}
}
}
| Layer | Technology | |-------|-----------| | Runtime | Node.js 22+ (ESM-only) | | Language | TypeScript 5.9 | | Agent | pi-coding-agent / claude-agent-sdk | | Database (gateway) | MySQL or SQLite (via sql.js) + Drizzle ORM | | Database (memory) | node:sqlite + FTS5 + bge-m3 embeddings | | Frontend | React + Vite + Tailwind CSS | | K8s Client | @kubernetes/client-node | | MCP | @modelcontextprotocol/sdk | | Realtime | WebSocket (ws) |
See CONTRIBUTING.md for development setup, architecture overview, and pull request guidelines.
Looking for a place to start? Check out issues labeled good first issue.