GitLab

The GitLab MCP server is now generally available. Agents can reach GitLab through its APIs, but they often guess at endpoints and use up their context window on extra calls. With the GitLab MCP server, any MCP-compatible agent can run core GitLab workflows from the client your team already works in, getting what it needs in fewer calls and with less context bloat. Agents can work across code, merge requests, work items, and pipelines, and hand work to GitLab Duo Agent Platform flows. Each action runs under your existing GitLab permissions. Learn more: https://lnkd.in/eYUZB9ur

A walking red flag in your workflow? An agent that acts first and explains later 🚩 Put it back in the loop. Some decisions still need your sign-off.

Speed you can trust, all the way to production. Learn more about the 19.5 release: https://lnkd.in/gJTgMFB9 With GitLab 19.5, you can connect any MCP-compatible agent to GitLab from the client your team already uses. You keep secrets under your existing permissions and get every merge request to the right reviewer, faster. Swipe to see what’s new.

Gemini 4 Argon is now available on GitLab Duo Agent Platform. As AI models take on longer, multi-step work, teams need results they can trust. In internal evaluations, Argon completed 93.3% of GitLab’s software engineering benchmark tasks. Your engineers can delegate the work with confidence and spend their time reviewing the result. Read the blog: https://lnkd.in/ezgbjajN

How do you build spacecraft faster without cutting corners on oversight and security? Intuitive Machines is using GitLab to build more efficiently and move faster. Brian Butcher, Software Group Lead, and Dami Alugo, Lead DevSecOps Engineer, share how AI is changing spacecraft development and where it could take the industry next. Listen to the full episode: https://lnkd.in/ey2GXRsr

AI agents are taking on more of the software development lifecycle, creating new demands for source control: more activity, more concurrency, and increasingly large repositories. GitLab has been developing next-generation source code management (SCM) to support thousands of concurrent agents working against large repositories. We announced this work at GitLab Transcend in June, joined on stage by Nick G. from Anthropic’s source control team. Anthropic’s new post today is a timely illustration of how quickly agentic development is scaling. GitLab is building on Git compatibility to help organizations manage this next phase of software development within a governed software factory. Read more on our blog: https://lnkd.in/eP5tkBqg

Gemini 4 Argon from Google DeepMind is now available on GitLab Duo Agent Platform, across all tiers and deployment models. Stuart Moncada, VP of Product Management at GitLab, shared why this matters for teams building with AI: “As software development becomes more agentic, teams need models that can support long-running, multi-step work across all stages of the development lifecycle. Gemini 4 Argon is designed to help organizations bring AI into development, security, and operations while keeping it within established enterprise workflows and controls.”

We are excited to recognize Dhairya Majmudar, a Level 3 contributor, as this month’s Notable Contributor! Dhairya contributed to offline transfer and Organizations support for import, so that groups, projects, and their memberships can move between GitLab instances. Learn more here: https://lnkd.in/edmiwPb8

Want to see how GitLab Artifact Central actually works? Principal Product Managers Tim Rizzi and Corinne Dent go deep on the architecture, the migration path, and what it means for teams building with AI agents. Watch the full deep dive above, then read more on the Artifact Central blog: https://lnkd.in/eFhg5vBp

GitLab CEO Bill Staples sat down with Darren Wilkes, CTO at COCC, to talk about how his team uses GitLab Duo. In this conversation, they touched on how hundreds of AI agents now carry COCC's engineering work from requirement to production, with everything traceable back to source. Watch the conversation: