ContextQMD
Back to Gitlabhq

GitLab Duo Agent Platform

doc/user/duo_agent_platform/_index.md

19.3.09.5 KB
Original Source

{{< details >}}

  • Tier: Premium, Ultimate
  • Offering: GitLab.com, GitLab Self-Managed, GitLab Dedicated

{{< /details >}}

{{< collapsible title="Model information" >}}

{{< /collapsible >}}

{{< history >}}

  • Introduced as a beta in GitLab 18.2.
  • For GitLab Duo Agent Platform on self-managed instances (both with self-hosted models and cloud-connected GitLab models), introduced in GitLab 18.4, as an experiment with a feature flag named self_hosted_agent_platform. Disabled by default.
  • Feature flag self_hosted_agent_platform enabled in GitLab 18.7.
  • Generally available in GitLab 18.8.
  • GitLab Duo Agent Platform and GitLab Credits supported on GitLab 18.8 and later.
  • Feature flag self_hosted_agent_platform removed in GitLab 18.9.

{{< /history >}}

The GitLab Duo Agent Platform is an AI-native solution that embeds multiple intelligent assistants ("agents") throughout the software development lifecycle.

  • Instead of following a linear workflow, collaborate asynchronously with AI agents.
  • Delegate routine tasks, from code refactoring and security scans to research, to specialized AI agents.

To get started, see Get started with the GitLab Duo Agent Platform.

Prerequisites

To use the Agent Platform:

To use the Agent Platform in your local environment:

  • Install an editor extension and authenticate with GitLab.
  • Have a project in a group namespace.
  • Have the Developer, Maintainer, or Owner role.

Generally available features

These features are generally available and consume GitLab Credits when used.

Features available on the Free tier require the purchase of GitLab Credits.

FeatureFreePremiumUltimate
Agentic Chat
Answer complex questions and autonomously create and edit files.{{< yes >}}{{< yes >}}{{< yes >}}
Code Suggestions
Get AI-powered suggestions as you write code.{{< yes >}}{{< yes >}}{{< yes >}}
Custom agents
Build team-specific agents for your unique development requirements.{{< yes >}}{{< yes >}}{{< yes >}}
External agents
Securely connect third-party integrations and tools to extend Agent Platform capabilities.{{< no >}}{{< yes >}}{{< yes >}}
Planner Agent
Plan, prioritize, and track work.{{< yes >}}{{< yes >}}{{< yes >}}
Data Analyst Agent
Analyze data and generate insights from your development metrics and project data.{{< yes >}}{{< yes >}}{{< yes >}}
Developer Flow
Convert issues into merge requests.{{< yes >}}{{< yes >}}{{< yes >}}
Code Review Flow
Automate code review tasks and enforce coding standards across your team.{{< yes >}}{{< yes >}}{{< yes >}}
Convert to GitLab CI/CD Flow
Convert legacy CI/CD pipelines to the GitLab CI/CD format.{{< yes >}}{{< yes >}}{{< yes >}}
Fix CI/CD Pipeline Flow
Diagnose and automatically fix failing CI/CD pipelines.{{< yes >}}{{< yes >}}{{< yes >}}
Software Development Flow
Create a full, multi-step plan before executing it.{{< yes >}}{{< yes >}}{{< yes >}}
MCP clients
Access GitLab resources and tools from any MCP-compatible AI client or IDE extension. <sup>1</sup>{{< yes >}}{{< yes >}}{{< yes >}}
Custom flows
Combine multiple agents to solve your business problems.{{< yes >}}{{< yes >}}{{< yes >}}
Resolve merge conflicts
Autonomously analyze merge conflicts, edit conflicting files, and push a resolution commit.{{< no >}}{{< yes >}}{{< yes >}}
Flow Creator Agent
Create custom flows for the AI Catalog.{{< no >}}{{< yes >}}{{< yes >}}
Resolve review discussions
Autonomously analyze a review discussion, push the requested changes, and resolve the thread.{{< no >}}{{< yes >}}{{< yes >}}
SAST False Positive Detection Flow
Automatically identify and filter out false positives in SAST security scans.{{< no >}}{{< no >}}{{< yes >}}
SAST Vulnerability Resolution Flow
Automatically generate fixes and remediation steps for SAST vulnerabilities.{{< no >}}{{< no >}}{{< yes >}}
Secret False Positive Detection Flow
Automatically analyze secret detection findings to identify potential false positives.{{< no >}}{{< yes >}}{{< yes >}}
Security Analyst Agent
Automate repetitive security tasks: Triage issues, analyze vulnerabilities, and generate fixes.{{< no >}}{{< no >}}{{< yes >}}

Footnotes:

  1. MCP clients do not consume credits directly. However, any Agent Platform usage, such as model requests made through an MCP client, might consume credits.

Beta features that consume credits

These features are in beta and their usage consumes GitLab Credits.

FeatureFreePremiumUltimate
Security Review Flow
Detects business logic vulnerabilities in merge requests.{{< no >}}{{< no >}}{{< yes >}}

Beta and experimental features that don't consume credits

These features are either beta or experimental and do not consume GitLab Credits.

For users on the Free tier, these beta and experimental features do not consume credits, but you require credits in your Monthly Commitment Pool to access them.

[!warning] When a feature becomes generally available, usage of the feature starts to consume GitLab Credits on all GitLab versions and on all offerings. Beta features that don't consume credits can change to generally available with usage billing at any time.

FeatureFreePremiumUltimate
Agent tool governance
Configure tool-level approval policies to gate sensitive agent actions with human approval at execution time.{{< yes >}}{{< yes >}}{{< yes >}}
AI audit event report
Browse and filter a unified record of GitLab Duo agent activity for compliance and governance purposes.{{< no >}}{{< yes >}}{{< yes >}}
CI Expert Agent
Create, debug, and optimize GitLab CI/CD pipelines.{{< yes >}}{{< yes >}}{{< yes >}}
External MCP servers
Connect custom agents to external data sources and third-party services using MCP servers.{{< no >}}{{< yes >}}{{< yes >}}
Agentic Breaking Change Resolution Flow
Analyze pipeline failures on dependency bump merge requests and create code fixes to resolve breaking changes introduced by the dependency update.{{< no >}}{{< no >}}{{< yes >}}