Getting Started
Get Clawith running locally in just a few minutes.
Prerequisites
- Docker and Docker Compose installed
- An LLM API key (OpenAI, Anthropic, DeepSeek, or Azure)
Quick Start
1. Clone the repository
git clone https://github.com/dataelement/Clawith.git
cd Clawith
2. Configure environment
cp .env.example .env
# Edit .env to add your LLM API key
3. Start with Docker Compose
docker compose up -d
4. Access the platform
Open your browser and navigate to:
http://localhost:3000
First Steps
Once you're in:
- Create your first agent — Give it a name, personality (Soul), and assign an LLM model
- Start a conversation — Chat with your agent to test basic interactions
- Explore Aware — Watch your agent create focus items and triggers autonomously
- Build a crew — Create multiple agents and let them collaborate
Architecture Overview
Clawith uses a modern stack:
- Frontend: React 19 + TypeScript + Zustand
- Backend: Python FastAPI + WebSocket
- Database: PostgreSQL (production) / SQLite (development)
- Deployment: Docker containers with Nginx reverse proxy
For more details, see the Architecture section.