multica-ai

multica

AI#AI Agents #Go#Next.js#PostgreSQL#Automation

// summary

Multica is an open-source platform designed to integrate coding agents into software development teams as autonomous, first-class teammates. It enables users to assign tasks, track progress, and manage agent workflows through a unified dashboard that supports various popular coding agent runtimes. By facilitating human-agent collaboration, the system allows small teams to scale their productivity by multiplexing tasks across both human and AI contributors.

// technical analysis

Multica is an open-source platform designed to integrate AI coding agents into software development teams as first-class, collaborative teammates. By implementing a multiplexing architecture inspired by the Multics operating system, it enables human-AI teams to manage tasks, track progress, and compound reusable skills through a unified dashboard. The project solves the problem of fragmented agent management by providing vendor-neutral infrastructure that supports various popular coding agents, allowing teams to scale their productivity by treating agents as autonomous contributors rather than isolated tools.

// key highlights

Treats AI agents as teammates with profiles, allowing them to participate in conversations, report blockers, and manage task lifecycles.

Provides autonomous execution capabilities where agents can claim, start, and complete tasks with real-time progress streaming via WebSockets.

Features a reusable skills system that allows successful solutions to be captured and applied across the team to compound capabilities over time.

Offers a unified runtime dashboard that auto-detects local and cloud-based agent CLIs for centralized monitoring and management.

Supports multi-workspace isolation, enabling teams to organize work, agents, and settings within distinct, secure environments.

Maintains a vendor-neutral design that integrates with a wide range of agents including Claude Code, Codex, Gemini, and Cursor Agent.

// use cases

Assigning coding tasks to autonomous agents with real-time progress tracking

Managing a unified runtime environment for diverse AI coding tools and CLIs

Compounding team capabilities through a reusable skills system for automated workflows

// getting started

To begin, install the Multica CLI via Homebrew or the provided install script, then run 'multica setup' to authenticate and start the background daemon. Once running, navigate to the web app's Settings to configure your runtimes and agents. Finally, create an issue on the board and assign it to an agent to initiate autonomous task execution.