How to build a coding agent - Part 1.0

#opensource #multica #codingagent #architecture

In this tutorial series, we build a coding agent that you can assign tasks on GitHub. In this part 1.0, we discuss:

Plan
Architecture
Table of content

This tutorial series is inspired by Multica, an open-source managed agents platform.

The plan

I noticed Multica repository has been trending on GitHub. With Multica, you can assign your GitHub issues to an agent you create via Multica platform and it picks up the work, writes code, report blockers, and update statuses autonomously.

Well, may you could just vibe code this entire Multica clone, but the reason I wrote this series is because I wanted to understand how Multica creates agents, how an issue can be assigend to an agent, how to executes in the background, underlying system architecture.

We use DeepWiki to understand the Multica's codebase architecture apply those principles in the project we build.

Multica uses Go in the backend, we will implement this in Python. Architecture and the concepts will be same, just that we use a different programming language. The goal is not to copy the exact way of Multica's architecture but rather take inspiration and implement.

Architecture

Let's just reiterate the tech stack:

Frontend:

React + Vite
TanStack Query

Backend:

FastAPI (Python)

Goal:

Create an Agent via the UI
Save this Agent info in the database
Assign a task on Github to this agent
Daemon implementation to complete the assigned task.

While we implement the above goals, we study the Multica's architecture and replicate the patterns in our project, frameworks may vary, but the principles would not change.