Using Pi with GitHub Agentic Workflows

Run Pi on GitHub events with GitHub Copilot, Anthropic, OpenAI, or Google inference.

Connect your account

Use the Copilot configuration below with copilot-requests: write, or configure COPILOT_GITHUB_TOKEN for personal subscription billing.

For another provider, set model: anthropic/<model>, openai/<model>, or google/<model> and configure its API key. Threat detection uses Copilot by default even when Pi uses another provider; supply Copilot authentication or select a detection engine.

Run a daily report

After setting up gh-aw, save this workflow:

.github/workflows/daily-status.md

---
on:
  workflow_dispatch:
  schedule: daily
permissions:
  contents: read
  issues: read
  pull-requests: read
  copilot-requests: write
engine: pi
model: copilot/auto
tools:
  github:
    toolsets: [issues, pull_requests]
safe-outputs:
  create-issue:
    title-prefix: "[status] "
---

# Daily repository status

Summarize open issues and recent pull request activity in one concise issue.

Compile with gh aw compile daily-status, then commit and push both the Markdown and generated lock file. Run it from the repository’s Actions tab or wait for its schedule.

Capabilities and limitations

Pi supports multiple providers, native MCP, and sub-agents. See the Pi reference for provider routing, tool restrictions, extensions, and SDK/RPC modes.

Next steps

• Pi technical reference
• Create a workflow
• Workflow examples
• Compare engines