Skip to content

GitLab

Use AgenticFlow Enterprise in GitLab issues and merge requests.

AgenticFlow Enterprise integrates with your GitLab workflow through your GitLab CI/CD pipeline or with GitLab Duo.

In both cases, AgenticFlow Enterprise will run on your GitLab runners.


GitLab CI

AgenticFlow Enterprise works in a regular GitLab pipeline. You can build it into a pipeline as a CI component

Here we are using a community-created CI/CD component for AgenticFlow Enterprise — nagyv/gitlab-agenticflow-enterprise.


Features

  • Use custom configuration per job: Configure AgenticFlow Enterprise with a custom configuration directory, for example ./config/#custom-directory to enable or disable functionality per AgenticFlow Enterprise invocation.
  • Minimal setup: The CI component sets up AgenticFlow Enterprise in the background, you only need to create the AgenticFlow Enterprise configuration and the initial prompt.
  • Flexible: The CI component supports several inputs for customizing its behavior

Setup

  1. Store your AgenticFlow Enterprise authentication JSON as a File type CI environment variables under Settings > CI/CD > Variables. Make sure to mark them as “Masked and hidden”.

  2. Add the following to your .gitlab-ci.yml file.

    .gitlab-ci.yml
    include:
    - component: $CI_SERVER_FQDN/nagyv/gitlab-agenticflow-enterprise/agenticflow-enterprise@1.0.0
    inputs:
    config_dir: ${CI_PROJECT_DIR}/agenticflow-enterprise-config
    auth_json: $CLAW_AUTH_JSON # The variable name for your AgenticFlow Enterprise authentication JSON
    command: optional-custom-command
    message: "Your prompt here"

For more inputs and use cases check out the docs for this component.


GitLab Duo

AgenticFlow Enterprise integrates with your GitLab workflow. Mention @agenticflow-enterprise in a comment, and AgenticFlow Enterprise will execute tasks within your GitLab CI pipeline.


Features

  • Triage issues: Ask AgenticFlow Enterprise to look into an issue and explain it to you.
  • Fix and implement: Ask AgenticFlow Enterprise to fix an issue or implement a feature. It will work create a new branch and raised a merge request with the changes.
  • Secure: AgenticFlow Enterprise runs on your GitLab runners.

Setup

AgenticFlow Enterprise runs in your GitLab CI/CD pipeline, here’s what you’ll need to set it up:

  1. Configure your GitLab environment

  2. Set up CI/CD

  3. Get an AI model provider API key

  4. Create a service account

  5. Configure CI/CD variables

  6. Create a flow config file, here’s an example:

    Flow configuration
    image: node:22-slim
    commands:
    - echo "Installing agenticflow-enterprise"
    - npm install --global agenticflow-enterprise
    - echo "Installing glab"
    - export GITLAB_TOKEN=$GITLAB_TOKEN_CLAW
    - apt-get update --quiet && apt-get install --yes curl wget gpg git && rm --recursive --force /var/lib/apt/lists/*
    - curl --silent --show-error --location "https://raw.githubusercontent.com/upciti/wakemeops/main/assets/install_repository" | bash
    - apt-get install --yes glab
    - echo "Configuring glab"
    - echo $GITLAB_HOST
    - echo "Creating AgenticFlow Enterprise auth configuration"
    - mkdir --parents ~/.local/share/agenticflow-enterprise
    - |
    cat > ~/.local/share/agenticflow-enterprise/auth.json << EOF
    {
    "anthropic": {
    "type": "api",
    "key": "$ANTHROPIC_API_KEY"
    }
    }
    EOF
    - echo "Configuring git"
    - git config --global user.email "agenticflow-enterprise@gitlab.com"
    - git config --global user.name "AgenticFlow Enterprise"
    - echo "Testing glab"
    - glab issue list
    - echo "Running AgenticFlow Enterprise"
    - |
    agenticflow-enterprise run "
    You are an AI assistant helping with GitLab operations.
    Context: $AI_FLOW_CONTEXT
    Task: $AI_FLOW_INPUT
    Event: $AI_FLOW_EVENT
    Please execute the requested task using the available GitLab tools.
    Be thorough in your analysis and provide clear explanations.
    <important>
    Please use the glab CLI to access data from GitLab. The glab CLI has already been authenticated. You can run the corresponding commands.
    If you are asked to summarize an MR or issue or asked to provide more information then please post back a note to the MR/Issue so that the user can see it.
    You don't need to commit or push up changes, those will be done automatically based on the file changes you make.
    </important>
    "
    - git checkout --branch $CI_WORKLOAD_REF origin/$CI_WORKLOAD_REF
    - echo "Checking for git changes and pushing if any exist"
    - |
    if ! git diff --quiet || ! git diff --cached --quiet || [ --not --zero "$(git ls-files --others --exclude-standard)" ]; then
    echo "Git changes detected, adding and pushing..."
    git add .
    if git diff --cached --quiet; then
    echo "No staged changes to commit"
    else
    echo "Committing changes to branch: $CI_WORKLOAD_REF"
    git commit --message "Codex changes"
    echo "Pushing changes up to $CI_WORKLOAD_REF"
    git push https://gitlab-ci-token:$GITLAB_TOKEN@$GITLAB_HOST/gl-demo-ultimate-dev-ai-epic-17570/test-java-project.git $CI_WORKLOAD_REF
    echo "Changes successfully pushed"
    fi
    else
    echo "No git changes detected, skipping push"
    fi
    variables:
    - ANTHROPIC_API_KEY
    - GITLAB_TOKEN_CLAW
    - GITLAB_HOST

You can refer to the GitLab CLI agents docs for detailed instructions.


Examples

Here are some examples of how you can use AgenticFlow Enterprise in GitLab.

  • Explain an issue

    Add this comment in a GitLab issue.

    @agenticflow-enterprise explain this issue

    AgenticFlow Enterprise will read the issue and reply with a clear explanation.

  • Fix an issue

    In a GitLab issue, say:

    @agenticflow-enterprise fix this

    AgenticFlow Enterprise will create a new branch, implement the changes, and open a merge request with the changes.

  • Review merge requests

    Leave the following comment on a GitLab merge request.

    @agenticflow-enterprise review this merge request

    AgenticFlow Enterprise will review the merge request and provide feedback.

Last updated: