GitLab Orbit lands in Google Antigravity: AI agents gain access to full-project context

GitLab integrated the Orbit lifecycle context graph into the Google Antigravity platform — now developers can install the integration directly from the MCP Store and give agents structured access to their GitLab instance data.

What is GitLab Orbit

Orbit indexes the entire GitLab instance and builds a knowledge graph: connections between groups, projects, users, tasks, merge requests, pipelines, vulnerabilities, and source code. The graph is accessible through two MCP tools: `query_graph` for executing structured queries and `get_graph_schema` for accessing available node types, properties, and relationships.

Before Orbit arrived, Antigravity agents could only see open files and the terminal. They didn't know which services depended on the code being changed, couldn't detect similar vulnerabilities in other projects, and didn't understand who historically worked with those files. The development lifecycle context remained locked in the DevSecOps platform, accessible only through custom scripts or copying between tabs.

What the integration provides

By connecting Orbit, an agent can answer questions that previously required multi-step manual searches:

• Which projects depend on this module and will the change break them?
• Are there any open vulnerabilities in the project?
• Who should review this merge request based on review history and file ownership?
• Which projects most often fail in the group's pipelines?

The agent formulates a query in Orbit's JSON DSL and receives a typed response — without switching between browser tabs. In early internal tests, agents connected to Orbit answered 11 times faster, used 4.5 times fewer tokens, and made 45 times fewer hallucinations.

Three key scenarios

Impact zone analysis. Before refactoring a shared authentication library, an engineer asks the agent: what depends on this module, which open merge requests affect these files, and who owns them? The agent makes one query to the graph and returns three answers simultaneously. The engineer sees what challenges the refactoring will face before making the first change.

Onboarding to a new service. A developer returning to unfamiliar code asks the agent to show dependencies, entry points, and this week's merge requests. The agent builds a 'Walkthrough Artifact' — a map of the service's current state, not an outdated wiki that typically awaits newcomers. Orbit re-indexes within minutes of any change, so the map is always fresh.

Dependency map. A tech lead requests the dependency structure of a group of services and asks the agent to render it as an architecture diagram. The graph is live — the diagram reflects the current state, not a schema that hasn't been maintained manually in ages. For a narrower slice, such as only services with open vulnerabilities, simply make another query and regenerate the diagram.

Installation and availability

Orbit can be installed in just a few clicks through the MCP Store in Antigravity settings: open the MCP section, click 'Add MCP', select GitLab Orbit, and authenticate through GitLab. No configuration files or terminal needed. After installation, Orbit tools are automatically available to all agents in the workspace.

Orbit is the same engine that powers GitLab Duo Agent Platform. Platform engineering teams get a single knowledge graph for both agents inside GitLab and agents in Antigravity, without a separate context pipeline. Ruby, Java, Kotlin, Python, TypeScript, JavaScript, Rust, and C# are supported. The integration is available for GitLab Premium and Ultimate tiers on GitLab.com.

What it means

The arrival of GitLab Orbit in Google Antigravity is a step toward AI agents working with real repository context instead of hallucinating due to its absence. Instead of custom scripts and copying between windows, developers get a structured knowledge graph directly in their work environment — and agents start giving answers that account for all the complexity of a live project.