Introducing GitLab Orbit
Close
To search repositories and projects, login to gitlab.com.
SuggestionsGitLab Duo Agent PlatformCode Suggestions (AI)CI/CDGitLab on AWSGitLab on Google CloudWhy GitLab?
The intelligent orchestration platform for DevSecOps<br>Explore our Platform Agentic AI for the entire software lifecycle<br>Meet GitLab Duo See the top reasons enterprises choose GitLab<br>Learn more
ProductAutomation<br>CI/CD<br>GitLab Duo Agent Platform<br>Source Code Management<br>Automated Software Delivery<br>Security<br>Application Security Testing<br>Software Supply Chain Security<br>Software Compliance<br>Measurement<br>Visibility & Measurement<br>Value Stream Management<br>Analytics & Insights
View all Solutions<br>GitLab for<br>Enterprise<br>Small Business<br>Public Sector
Pricing<br>ResourcesGetting started<br>Install<br>Quick start guides<br>Learn<br>Product documentation<br>Best practice videos<br>Integrations<br>Discover<br>Customer success stories<br>Blog<br>The Source<br>Remote<br>Connect<br>GitLab Services<br>Community<br>Forum<br>Events<br>Partners
View all resources<br>Stay updated with our latest features and improvements.
Read the latest
Company<br>About<br>Jobs<br>Events<br>Leadership<br>Team<br>Handbook<br>Investor relations<br>Trust Center<br>AI Transparency Center<br>Newsletter<br>Press
Contact us<br>Talk to sales<br>Support portal<br>Customer portal
Talk to salesGet free trialSign in<br>Published on: June 10, 2026<br>7 min read
Introducing GitLab Orbit: Full code and lifecycle context, in one query<br>With Orbit, your software agents are up to 11 times faster, use up to 4.5 times fewer tokens, and answer questions you couldn’t before.
Rebecca Carter<br>product<br>ai<br>news<br>features
Agents are good at writing code. They're far worse at navigating the system around it: the related code, the pipelines that run it, the deployments that ship it, the work items that asked for it, and the teams that own it. That gap is where AI-assisted engineering breaks down today.<br>In a large monorepo, the gap shows up as wasted iterations, blown token budgets, and code that looks correct but gets reverted. Across repos, it's worse: the context window fills before the agent finds the answer, and the task fails outright. Teams end up spending more time fixing agent output than the agent saved them.<br>GitLab Orbit, now in public beta, closes the gap. It's a live, queryable graph of all your code, merge requests, pipelines, deployments, vulnerabilities, and ownership, with every relationship between them kept current as your team works. Agents reason from first-party GitLab data instead of stitched-together tool calls. Engineers can query the same graph through the Data Explorer to trace changes, investigate incidents, and answer the cross-system questions that today take hours of manual reconstruction.<br>Proven on real merge requests at Compare the Market<br>Compare the Market, a U.K. price comparison platform, tested four context retrieval approaches for an internal AI code reviewer across 79 real merge requests. The Orbit-grounded reviewer placed accurate inline comments about 70% of the time, against about 58% for retrieval-augmented generation (RAG), and captured more of the key changes in summaries (68% vs. 66%). RAG underperformed every other approach, including no context at all.<br>"Orbit gave us an AI code reviewer that actually understands our codebase, not just the diff in front of it. We tested it against RAG and a few other approaches across real merge requests, and the gap was clear. Better comment placement, better summaries of what actually changed. RAG, which we'd assumed would be the natural solution, ended up performing worse than no context at all. For us, that result spoke for itself."
- Ryan Harvey, Head of AI Engineering, Compare the Market<br>What you can do with GitLab Orbit<br>Here are two examples of how you can use GitLab Orbit in your environment.<br>Scenario 1: With Claude Code or other coding agents<br>The work you already do, faster and more accurate<br>Say, you already run Claude Code. When you point it at a large monorepo, it spends its first stretch, and a real share of its token budget, just crawling files to work out where things live and what connects to what. In a big enough codebase it follows the wrong threads, misses a dependency, or runs out of room before it starts the actual work.<br>Connect Claude Code to GitLab Orbit through Model Context Protocol (MCP) and it stops crawling. It asks the graph the questions it was trying to reconstruct by iterating where does this code live, what depends on it, which tests and pipelines cover it. Instead, it gets a precise answer in one or two queries. On the same tasks, with the same model, it’s up to 11 times faster, uses up to 4.5 times fewer tokens, and generates up to 45 times fewer hallucinations.<br>Scenario 2: With GitLab Duo Agent Platform<br>Answers that were never possible before<br>Some questions were never really answerable by an agent, because the answer isn't in the code — it's in how code connects to pipelines, deployments, vulnerabilities, and ownership across your whole system. Agents on GitLab Duo...