Solution

AI coding agent infrastructure: access, runtime and review

A coding agent writes code. Turning that into a running application takes project access, an environment to work in, and a pipeline that checks and ships its changes.

MCP server, ap CLI and VS Code plugin as the connection to your project
Cloud workspaces where longer agent runs keep going without your machine
GitLab CI pipelines that test and build every change

Start for free. No credit card required.

A prepared project structure gives agents a reliable starting point.

In short

The platform does not make agents smarter. It makes sure their work lands somewhere defined and gets checked.

Access: an MCP server, the ap CLI, a VS Code plugin and personal API keys connect tools to your project.
Runtime: cloud workspaces with VS Code, JetBrains, RDP and VNC keep running once you close your laptop.

Coding agents with and without a platform

This lays out the tasks that surround coding agents and how much of each the Application Platform covers.

Criterion	With the Application Platform	Without a platform
Access to project context	Fully covered: An MCP server connects agents to the project, repositories and environments	Partly covered: The agent only sees the local folder it was started in
Editor integration	Fully covered: VS Code plugin with project overview, repositories and run commands	Partly covered: Editor configuration is maintained per machine by hand
Terminal integration	Fully covered: ap CLI for project commands and running applications locally	Partly covered: Homegrown scripts that drift apart between projects
Automation through an API	Fully covered: Personal API keys for your own workflows and tools	Not offered: Individual service credentials, scattered and hard to revoke
Runtime for longer tasks	Fully covered: Cloud workspaces keep working while your machine is off	Not offered: Runs locally and stops when the notebook sleeps
A dependable starting point	Fully covered: Templates and a defined project structure with conventions	Not offered: Empty repository, conventions emerge along the way
Checking the output	Fully covered: GitLab CI tests and builds every change before it ships	Partly covered: A pipeline has to be built first, otherwise nothing checks
Errors after release	Fully covered: Sentry is set up automatically, errors arrive with stack trace and release	Partly covered: A separate setup per project, or none at all
Traceability	Fully covered: Audit log plus GitOps configuration in the Git history	Not offered: Environment changes stay hidden in server state
Permissions and access	Fully covered: Roles, organisations and centrally managed credentials	Partly covered: Agents inherit the permissions of whoever started them

Green means covered, amber partly, grey not available. The right column describes no competitor but the usual situation without an end-to-end platform.

As of 10 August 2026. This comparison describes typical workflows and can differ from project to project.

What the platform provides for agents

Six building blocks that sit between a suggestion in a chat window and a shipped change.

MCP server

Through the MCP server, coding agents reach the project, its repositories and environments instead of guessing inside an empty folder.

ap CLI and VS Code plugin

The CLI covers project commands and local runs, while the plugin surfaces repositories, tech stack and shortcuts inside the editor.

Cloud workspaces

Agents keep running in a cloud VM with VS Code, JetBrains, RDP or VNC while your own device is switched off.

Project structure to build on

Personal API keys, roles and an audit log make it visible who or what triggered a change.

acme / customer-app

kunden-app
Flutter app for iOS, Android, and web
backend
API and server logic with Docker setup
homepage
Marketing site and public content
e2e-tests
End-to-end tests against dev and staging
gitops-configuration
Deployment configuration for dev and prod
local-configuration
Workspace, IDE, and agent configuration
gitlab-profile
Project documentation and README

Repositories, deploy keys and CI variables are created with the project.

Connecting coding agents to a project

Four steps from signing up to a first checked result.

Create a project from a template

Repository, project structure, pipeline and environments come out of the wizard, giving the agent a defined baseline.
Connect your tools

Set up the MCP server for your agent, install the VS Code plugin or use the ap CLI inside the project folder.
Choose where work happens

Work locally with the Platform App, or start a cloud workspace when a run outlasts your attention span.
Let the pipeline check it

Changes arrive as commits and travel through the pipeline. Whatever fails there does not ship, no matter who wrote it.

Frequently asked questions

Does the platform improve what AI agents produce?

No. Output quality depends on the model and on how you frame the task. The platform only shapes the setting: every change runs through the same tests and build steps as hand-written code. Judging whether a suggestion is correct remains your job.

Which tools can be connected?

Through open paths, not tool-specific integrations. Agents that speak MCP use the platform's MCP server, editors based on VS Code use the plugin, anything else connects through the ap CLI or API keys. That covers Claude Code, Cursor, Codex and Copilot.

Why use a cloud workspace if the agent runs locally?

Credentials live centrally in the project, not in source code, and the project conventions rule out committing secrets. What an agent can reach depends on the API key or account it operates under; for sensitive environments, use reduced permissions.

Point your agent at a real project