explaingit

multica-ai/multica

📈 Trending★ 29,261TypeScriptAudience · developerComplexity · 4/5ActiveSetup · moderate

TLDR

Assign coding tasks to AI agents like Claude and Copilot as if they were team members. They work autonomously, report progress, and save solutions as reusable skills.

Mindmap

mindmap
  root((Multica))
    What it does
      Assign tasks to AI agents
      Autonomous code execution
      Real-time dashboard
      Reusable skills library
    How it works
      Background daemon process
      Multi-agent routing
      Activity timelines
      Progress streaming
    Supported agents
      Claude Code
      GitHub Copilot CLI
      Cursor Agent
      Gemini
    Deployment
      Multica Cloud
      Self-hosted Docker
    Use cases
      Parallel task execution
      Team delegation
      Skill accumulation

Things people build with this

USE CASE 1

Assign multiple coding tasks to different AI agents and have them work in parallel without manual oversight.

USE CASE 2

Build a library of reusable solutions as agents complete tasks, growing your team's collective capability over time.

USE CASE 3

Monitor all agent activity and progress from a single real-time dashboard instead of juggling multiple tool windows.

USE CASE 4

Self-host an AI agent platform on your own infrastructure using Docker for full control and privacy.

Tech stack

TypeScriptDockerNode.jsWeb dashboard

Getting it running

Difficulty · moderate Time to first run · 30min

Docker required to run; needs API keys for Claude/Copilot integration.

License could not be detected automatically. Check the repository's LICENSE file before use.

In plain English

Multica is an open-source platform that lets you treat AI coding agents, like Claude Code, Codex, GitHub Copilot CLI, Cursor Agent, or Gemini, as actual members of your development team. Instead of manually prompting an AI tool for each task, you assign issues to agents the same way you would assign work to a human colleague. The agent picks up the task, writes code, reports blockers, posts updates, and marks work complete, all autonomously. The platform manages the full lifecycle of each agent task: from assignment through execution to completion. It uses a background daemon (a persistent background process) that runs on your computer or in the cloud, detects which AI CLI tools are available, and routes work accordingly. A real-time web dashboard shows all your agents on a task board with activity timelines and progress streaming. As agents solve problems, their solutions can be saved as reusable skills, so the team's collective capability grows over time. You would use Multica if you are a developer or small team wanting to delegate coding tasks to AI agents without babysitting each run, or if you want multiple agents working in parallel on different issues. It can be used via Multica Cloud or self-hosted with Docker. The project is written in TypeScript.

Copy-paste prompts

Prompt 1
How do I set up Multica to assign my first coding task to Claude Code and track its progress on the dashboard?
Prompt 2
Show me how to configure multiple AI agents in Multica so they can work on different GitHub issues in parallel.
Prompt 3
How do I save a solution from a completed agent task as a reusable skill in Multica?
Prompt 4
What's the process for self-hosting Multica with Docker instead of using Multica Cloud?
Prompt 5
How do I integrate Multica with my GitHub repository to automatically assign issues to available agents?
Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.