HagiCode Product Overview

HagiCode is an AI workspace for project development. Start with a session to understand a repository, define the request and its scope, let AI make changes, and review progress, prepare commits, and reuse project knowledge in one place. It connects the Agent CLI and models you use rather than requiring a particular code editor.

New here? Choose an installation method, complete the setup wizard, create a project, and start with a conversation session. If the task calls for planning before implementation, use a proposal session.

How a development task works

For example, suppose you need to change a feature spanning several repositories:

1. Understand first: Analyze the existing code in a conversation session. Conversation sessions are read-only by default; switch to edit mode when you need to change files.
2. Define the scope: For a complex change, select the project and repositories in a proposal session. Outline the goals, tasks, and verification steps before proceeding with execution.
3. Track the outcome: Review sessions and execution status in the workspace. When you need to prepare a commit, use AI Compose Commit.
4. Keep the context: Revisit proposals and commit history. For cross-repository work, use MonoSpecs to manage repository relationships and change scope.

You do not need a proposal for every task. Start with a conversation session when you only want to explore the code or handle a simple issue. HagiCode provides a traceable path when a task needs more context.

Explore features by need

If you want to…	Start here
Understand the code before deciding whether to edit it	Create a conversation session
Plan before implementing a complex request	Create a proposal session
Help AI understand how multiple repositories relate	MonoSpecs guide
Find, install, and manage extensions	Skills guide
Use a familiar Agent CLI	AI Agent CLI installation and support
Manage CLI and model connections separately	OmniRoute installation and startup checks

Vault brings together reference repositories, folders, and notes for later work; Code Server offers an editing entry point in the browser. Neither is required to get started with HagiCode. For the design background, see Working with the Vault knowledge base and Browser editing integration.

HagiCode also offers feedback through heroes, achievements, daily reports, and Token metrics to make status and progress more visible over time. These are part of the workspace experience, not a requirement for using it as a regular development tool. See the article on gamification design.

Editions & Pricing

Desktop, Container, and Microsoft Store are different ways to obtain or deploy HagiCode, not three paid tiers. Core features are free to use. Turbo Engine in the Microsoft Store channel is a separate, one-time license that unlocks a higher proposal concurrency limit and enhancements such as documentation themes, custom attribution, branding, and avatars. See the Turbo Engine add-on for the specific features it unlocks.

Your environment	Recommended option
Windows with access to Microsoft Store	Install from Microsoft Store
Manual Windows installation, or local use on macOS or Linux	Install Desktop
Server, NAS, or team deployment	Install with Docker Compose

The Steam main application has been retired and is no longer an installation channel. See Steam distribution status.

Where to start

Choose an installation methodFind the right option for your operating system and deployment environment.

Complete the setup wizardConfigure the basics after first launch and create at least one project.

Create a conversation sessionStart by exploring your project in read-only mode, then decide whether to edit or create a proposal.

Why make it a workspace?

I’m Kun Yu, the creator of HagiCode. A single question and answer can solve an immediate problem, but real development also means understanding the project, setting boundaries, carrying changes through, and reviewing the result. I wanted to bring these scattered steps together; gamified feedback makes progress in long-running work easier to see. You can use just some of these features. You do not have to learn every module before you start coding.

If you would rather see the product in action, watch the demonstration video below.

Real Product Walkthroughs

See Hagicode in real coding sessions

Start with the English YouTube overview embedded below, then compare two supporting Bilibili demos without losing the product story or the direct watch links.

Featured walkthroughYouTube

Hagicode Product Overview on YouTube

This is the primary English-language product introduction, so readers can understand Hagicode's workflow, product scope, and multi-agent angle before leaving the docs page.

Open on YouTube

Focused demoBilibili

AI Playing Games While Coding

A supporting Bilibili demo that shows the product feeling playful and alive during real coding sessions instead of behaving like a dry code generator.

Open on Bilibili

Focused demoBilibili

GPT Codex in Hagicode: Live Trial

A narrower validation run that helps readers judge how GPT Codex behaves inside the actual Hagicode product after the main YouTube introduction.

Open on Bilibili