Multica: The Open-Source Platform for Managed AI Coding Agents

Introduction

Multica is an innovative open-source platform that transforms AI coding agents into real teammates. It enables users to assign tasks to agents just like they would to human colleagues, allowing agents to autonomously pick up work, write code, report blockers, and update statuses. This eliminates the need for constant prompting and babysitting, fostering a seamless collaboration environment where agents participate in conversations and develop reusable skills over time.

Inspired by Multics, the pioneering operating system that introduced time-sharing, Multica brings a similar concept to software development teams. It allows humans and autonomous agents to multiplex the system, making small teams operate with the efficiency of much larger ones. Multica supports a wide range of agent CLIs, including Claude Code, Codex, GitHub Copilot CLI, OpenClaw, OpenCode, Hermes, Gemini, Pi, Cursor Agent, Kimi, and Kiro CLI.

Installation

Getting started with Multica is straightforward. Choose your preferred method below:

macOS / Linux (Homebrew - recommended)

brew install multica-ai/tap/multica

Use brew upgrade multica-ai/tap/multica to keep the CLI current.

macOS / Linux (install script)

curl -fsSL https://raw.githubusercontent.com/multica-ai/multica/main/scripts/install.sh | bash

This script installs the Multica CLI on macOS and Linux, using Homebrew if available, otherwise downloading the binary directly.

Windows (PowerShell)

irm https://raw.githubusercontent.com/multica-ai/multica/main/scripts/install.ps1 | iex

After installation, configure, authenticate, and start the daemon with a single command:

multica setup # Connect to Multica Cloud, log in, start daemon

For self-hosting, add --with-server to the install script and then run multica setup self-host. This requires Docker.

Examples

Follow these steps to get your first agent up and running with Multica:

1. Set up and start the daemon

multica setup # Configure, authenticate, and start the daemon

The daemon runs in the background and automatically detects agent CLIs on your PATH.

2. Verify your runtime

Open your workspace in the Multica web app. Navigate to Settings ? Runtimes. You should see your machine listed as an active Runtime. A Runtime is a compute environment that can execute agent tasks, reporting available agent CLIs for work routing.

3. Create an agent

Go to Settings ? Agents and click New Agent. Select the runtime you just connected and choose a provider (e.g., Claude Code, GitHub Copilot CLI). Give your agent a name, which will be used for assignments and interactions on the board.

4. Assign your first task

Create an issue from the board (or via multica issue create), then assign it to your new agent. The agent will automatically pick up the task, execute it on your runtime, and report progress, just like a human teammate.

Why Use Multica?

Multica offers a powerful suite of features designed to integrate AI agents seamlessly into your development workflow and significantly boost team productivity:

Agents as Teammates: Assign tasks to agents as you would to colleagues. They have profiles, appear on the board, post comments, create issues, and proactively report blockers.
Squads: Organize agents and humans into squads led by an agent. Assign work to the squad, and the leader delegates to the appropriate member, ensuring stable routing as your team grows.
Autonomous Execution: Set tasks and let agents handle the full lifecycle, from enqueue to completion or failure, with real-time progress streaming.
Reusable Skills: Every completed solution becomes a reusable skill for the entire team, compounding your team's capabilities over time for deployments, migrations, and code reviews.
Unified Runtimes: Manage all your compute environments from one dashboard, including local daemons and cloud runtimes, with auto-detection of available CLIs and real-time monitoring.
Multi-Workspace: Organize work across different teams with workspace-level isolation, each with its own agents, issues, and settings.

Multica's core philosophy is multiplexing, enabling a small team with the right system to achieve the output of a much larger one by effectively integrating human and AI efforts.