Content your team can actually manage
Pages built from reusable sections, articles and products, categories, images and translations — all editable by the people who own them, without touching application code.
The content backend you don't have to build
Build your product. Don't build the content system around it.
Garchi gives your site or app a ready-made home for pages, articles, product data, images and translations. Your app reads it through the API, your team manages it in the dashboard, and your AI tools can work with it through MCP.
No CMS to host. No admin panel to build. No deploy to change a headline.
Free Sandbox plan · no card required
The problem
AI can build the site. Someone still has to manage the content.
Your app is finished. The content work isn't.
- Marketing wants the pricing headline changed.
- A product price is wrong.
- There is a new article to publish.
- The hero image is out of date.
- A page needs a German version.
- The campaign copy changes on Friday.
None of that should need a branch, a pull request or a deploy. None of it should mean prompting an AI coding tool to go and edit your frontend again. And none of it should mean building an admin panel first.
Why Garchi
Everything your app needs from a content backend
You could assemble this yourself. It is rarely the interesting part of the product you set out to build.
An API your frontend can rely on
Your application stays yours. Garchi holds the content behind it and serves it over REST, with Node.js and PHP SDKs and starter kits for Next.js, Nuxt, SvelteKit and Laravel.
AI access without building the plumbing
Compatible AI clients work with the same content through Garchi's MCP server, so there is no separate agent integration for you to write and keep working.
Hosted and ready
No CMS server to run, no admin system to build, no content infrastructure to maintain. Separate projects get separate spaces, each with their own content and collaborators.
How it works
Your code declares the fields. Garchi holds the values.
Your component says what it needs. The same fields show up in Garchi, where anyone on your team can fill them in and change them later.
StepItem.tsx
type Props = { step_number?: string; title?: string; description?: string; icon?: string; [x: string]: any;}; export default function StepItem({ step_number, title, description, icon, ...props}: Props) { return ( … );}It declares the fields it needs. Nothing else.
Those same fields, filled in — and the page updating beside them.
The same four fields, in both places
step_number
title
description
icon
-
Your frontend stays yours
Build it with your preferred framework, your own developers or an AI coding tool. Garchi does not replace your frontend, your hosting or your application architecture.
-
Garchi holds the content
The text, images and data behind it move out of your repo and into Garchi, where they can change without the code changing.
-
Your team manages it from there
Updating a headline, fixing a price or publishing an article stops being a developer's job.
- Your team
- uses the dashboard.
- Your app
- reads the REST API.
- Your AI tools
- use MCP.
All three work on the same content. Use the dashboard, the API or MCP depending on the task.
Starter kits
Scaffold a connected project with one command
Starter kits for Next.js, Nuxt, SvelteKit and Laravel. Or skip the kit and call the REST API from any stack.
npx @lumenharbor/garchi-starter-kit -k next
Content modelling
Content models that fit your product
Your blog post has authors. Your product page has pricing tiers. Your case study has industry tags. Garchi's data items start with a base schema and extend with the metadata your content needs — without changing your application's database schema.
BUILT-IN MCP SERVER
Your AI tools can work with the CMS too
Connect a compatible AI client and it works against your real content model: drafting pages, updating items, reordering sections, using the assets already in your space. The work is saved into Garchi rather than pasted in by hand afterwards.
MCP is the open standard that makes the connection possible, and it is already built in — there is no agent integration for you to write. Agent changes stay in draft until someone publishes them.
CONNECT YOUR AI CLIENT
WORKS ON YOUR REAL CONTENT MODEL
20+ TOOLS
YOUR AI AGENT
The agent reads your content model and calls the same operations your team uses in the dashboard.
The part that makes it safe
Let an agent near your content. Not near your live site.
Nobody is worried that the AI can't write. They are worried about what happens when it writes the wrong thing. Changes stay reversible, and off your live site until you publish them.
You would rather see a change before your customers do.
Nothing goes live on its own
Everything an agent writes stays a draft. It reaches the public only when a person publishes it.
You notice it days later, and nobody remembers what it said before.
Changes leave a trail you can walk back
Every change leaves a restore point for 30 days, labelled with who made it. Rolling back takes a click.
Reading a diff doesn't tell you whether the page actually looks right.
See it on your real site first
Drafts render on your own frontend, visible to you and nobody else, until you are happy with it.
Last deploy
6 days ago
Last content change
4 min ago
Fixing one word means a pull request and a deploy.
Nobody deploys to fix a typo
Content lives outside your codebase. Whoever changes it, you ship code only when the code changes.
Also included
Multilingual content per space
Hosted, maintained and upgraded for you
A REST API any stack can call
Node.js and PHP SDKs
Notes on your content that agents can read
Separate spaces with per-space collaborators
Publishing
Publish without building another integration
Need something on LinkedIn, Instagram or Facebook? Draft it in Garchi, get it approved, then publish or schedule it from the same place as the rest of your content.
From draft to published
-
Draft
Write it, or let an agent draft it from content you already have.
-
Approve
Someone reads it and signs it off.
-
Schedule
Send now or set a time. Editing an approved post reopens the approval.
-
Publish
Garchi posts to each channel and records what happened on each one.
An agent can draft a post and send it for approval. It cannot approve, schedule or publish one. There is no tool for that.
Channels you can connect
- LinkedIn — Company pages and personal profiles
- Instagram — Business and Creator accounts
- Facebook — Pages
Images and video both work. Every plan includes a number of publishes, and every post keeps a record of what was sent and what each channel did with it.
Keep the tools you already use
Already use a dedicated social platform? Keep it. Garchi handles straightforward publishing from your content workflow, and your existing tools carry on with engagement, analytics, listening and broader campaign management.
Who it's for
Who Garchi is for
The situations differ. The problem underneath is the same.
Building with AI
Keep the copy out of the generated code
You prompted the frontend into existence. Now every wording change means going back and prompting again. Put that content in Garchi instead, where the same agents can still help with it through MCP.
SaaS and product teams
Let non-developers change the site
Give non-developers somewhere to manage landing pages, articles and product copy. Developers keep the architecture, and ship code only when the code changes.
Agencies and client projects
Hand the client the keys
Build the site, then hand the client somewhere to manage it. Paid plans include several spaces, each with its own content and collaborators, so clients never see each other's work.
Product tour
See Garchi CMS in action
Start with one space. Add the rest when you need it.
Create a space, add your content, point your frontend at it. Sandbox is free. You can connect an agent later, or never.
Free Sandbox plan · no card required