This document is designed for AI agents to execute. Follow these steps exactly to deploy a local Multica instance and connect to it.
- Docker and Docker Compose installed
- Homebrew installed (for CLI)
- At least one AI agent CLI on PATH:
claudeorcodex
curl -fsSL https://raw.githubusercontent.com/multica-ai/multica/main/scripts/install.sh | bash -s -- --localThis installs everything: clones the repo, starts Docker services, and installs the CLI.
Wait for the output ✓ Multica is installed and running! before proceeding.
Expected result:
- Frontend at http://localhost:3000
- Backend at http://localhost:8080
multicaCLI installed and configured for localhost
git clone https://github.com/multica-ai/multica.git
cd multica
make selfhost
brew install multica-ai/tap/multica
multica setup --localThe multica setup --local command will:
- Configure CLI to connect to localhost:8080 / localhost:3000
- Open a browser for login — use verification code
888888with any email - Discover workspaces automatically
- Start the daemon in the background
multica daemon statusShould show running with detected agents.
# Stop the daemon
multica daemon stop
# Stop all Docker services
cd multica
make selfhost-stopIf the default ports (8080/3000) are in use:
- Edit
.envand changePORTandFRONTEND_PORT - Run
make selfhost - Run
multica setup --local --port <PORT> --frontend-port <FRONTEND_PORT>
- Backend not ready:
docker compose -f docker-compose.selfhost.yml logs backend - Frontend not ready:
docker compose -f docker-compose.selfhost.yml logs frontend - Daemon issues:
multica daemon logs - Health check:
curl http://localhost:8080/health