What you need

A server or local machine with Docker and Docker Compose installed.

At least 4 GB of RAM and 10 GB of free disk space.

An OpenAI API key or compatible model provider key.

Basic familiarity with the terminal.

Step 1: Clone the repository

Run `git clone https://github.com/openclaw/openclaw.git` and `cd openclaw`.

This pulls the latest version of OpenClaw including the Docker Compose configuration.

Step 2: Configure environment variables

Copy the example env file: `cp .env.example .env`.

Open `.env` and add your model provider API key. For OpenAI, set `OPENAI_API_KEY=sk-your-key-here`.

Optionally configure the port (default 3000) and enable additional features like web search or file storage.

Step 3: Start the services

Run `docker compose up -d` to start OpenClaw and its supporting services (Postgres, Redis).

The first start may take a few minutes as Docker pulls images. Subsequent starts are instant.

Check the logs with `docker compose logs -f` to confirm all services are healthy.

Step 4: Access the dashboard

Open your browser to `http://localhost:3000` (or your configured port).

Create an admin account — this is your dashboard login for managing agents, tools, and workflows.

You will see the OpenClaw dashboard with the agent directory, workflow builder, and system monitor.

Step 5: Create your first agent

Click 'Create Agent' and give it a name like 'Research Assistant'.

Define its role: 'A research specialist that finds, summarizes, and cites sources on any topic.'

Assign tools: web search, content retrieval, and summarization. Save the agent.

Step 6: Run a test task

Create a new task: 'Research top trends in AI agent harnesses for 2026 and provide a summary with sources.'

Assign it to your Research Assistant agent and click Run.

Watch the agent work through the steps in real time. Review the output before approving it.

FAQ

Can I run OpenClaw without Docker?

Docker is the recommended and most tested path. Manual installation is possible but requires Node.js, Postgres, and Redis configured independently.

Does OpenClaw work with local LLMs?

Yes. OpenClaw supports any OpenAI-compatible API, which means you can point it at Ollama, vLLM, or LocalAI running locally.

How do I add team members?

OpenClaw supports multi-user via the dashboard admin panel. Invite team members by email and assign role-based permissions.

Deploy OpenClaw

  1. Clone the repository: git clone https://github.com/openclaw/openclaw.git
  2. Configure .env with your API key
  3. Run docker compose up -d
  4. Access http://localhost:3000 and create an admin account
  5. Create an agent with a role and tools
  6. Run a test task and review the output

Products that work with this harness

These business kits are designed to install and run on OpenClaw. Each includes pre-configured agent roles, prompts, workflows, and approval gates.

Ready to see the full catalog?

Browse all 42 agent-ready business kits. Each includes pre-configured agent roles, prompts, workflows, install steps, and approval gates.

Shop all business kits