Show HN: Local automation runner with built-in LLM steps – YAML pipelines

Stepyard, a new open-source automation runner, lets developers define YAML pipelines with built-in LLM steps and Python plugins, running entirely on local machines without cloud dependencies. The tool supports scheduled and on-demand execution, with state stored locally in SQLite, and aims to simplify CI/CD and automation workflows.

Stepyard ¶ stepyard YAML pipelines. Python plugins. Runs on your machine - no server to set up, no cloud account needed. Stepyard is an automation runner for developers. Pipelines live as YAML files in your repo. You extend them with plain Python functions. Everything runs from the CLI or a local daemon - on your machine or a server you own. pip install stepyard stepyard init my-project && cd my-project stepyard run hello A deploy pipeline: build and push a container, run a smoke test, and post the result to Slack. One YAML file, no supporting scripts. name: deploy description: Build, push, and verify the production container. steps: - id: build uses: shell.run with: command: docker build -t myapp:${{ env.GIT SHA }} . - id: push uses: shell.run with: command: docker push myapp:${{ env.GIT SHA }} - id: smoke test uses: http.request with: url: https://staging.myapp.com/healthz method: GET - id: notify uses: llm.generate built-in - no plugin needed with: model: gpt-4o-mini prompt: | Summarise this deploy result in one sentence for Slack: HTTP status: ${{ steps.smoke test.output.status }} SHA: ${{ env.GIT SHA }} - id: post to slack uses: http.request with: url: ${{ env.SLACK WEBHOOK }} method: POST json body: text: ${{ steps.notify.output.output }} Run it: GIT SHA=$ git rev-parse --short HEAD stepyard run deploy ✓ build 12.4 s ✓ push 4.1 s ✓ smoke test 0.3 s ✓ notify 0.9 s ✓ post to slack 0.2 s Flow completed in 18.0 s Why Stepyard? ¶ why-stepyard - Flows are files in your repo Steps, conditions, loops, and retries are plain YAML keys - no proprietary DSL. Version-control them alongside your code and validate them with stepyard validate . - Extend with plain Python One @node decorator turns any function into a reusable step. Inputs are type-validated automatically; plugin dependencies are isolated so they never conflict with Stepyard's own. - Nothing leaves your machine State is stored in a local SQLite database. Data goes out only if a step in your flow explicitly sends it. - Scheduled and on-demand execution cron , interval , and startup triggers. Run stepyard service start and your flows execute on schedule - no external service or cloud account needed. Real-world examples ¶ real-world-examples Daily database backup ¶ daily-database-backup name: pg backup trigger: uses: cron with: schedule: "0 3 " every day at 03:00 steps: - id: dump uses: shell.run with: command: pg dump ${{ env.DATABASE URL }} | gzip /tmp/backup.sql.gz - id: upload uses: shell.run with: command: | aws s3 cp /tmp/backup.sql.gz \ s3://${{ env.BACKUP BUCKET }}/db/$ date +%Y-%m-%d .sql.gz - id: cleanup uses: shell.run with: command: rm -f /tmp/backup.sql.gz Automated code review on every PR ¶ automated-code-review-on-every-pr Fetch the diff via the GitHub API, review it with an LLM, and post a comment back - all with built-in nodes, no additional service. name: pr review description: Review a PR diff with an LLM and post a comment if issues are found. Run: PR=42 GITHUB REPO=my-org/my-repo stepyard run pr review steps: - id: diff uses: http.request with: url: https://api.github.com/repos/${{ env.GITHUB REPO }}/pulls/${{ env.PR }}/files headers: Authorization: Bearer ${{ env.GITHUB TOKEN }} Accept: application/vnd.github+json - id: review uses: llm.generate with: model: gpt-4o system prompt: | You are a senior engineer doing a code review. Be concise. If everything looks good reply with exactly: LGTM prompt: | Review this pull request for bugs, security issues, and obvious mistakes: ${{ steps.diff.output.body }} - id: post comment if: ${{ steps.review.output.output = "LGTM" }} uses: http.request with: url: https://api.github.com/repos/${{ env.GITHUB REPO }}/issues/${{ env.PR }}/comments method: POST headers: Authorization: Bearer ${{ env.GITHUB TOKEN }} Accept: application/vnd.github+json json body: body: ${{ steps.review.output.output }} Multi-environment deployment with rollback ¶ multi-environment-deployment-with-rollback name: deploy multi steps: - id: deploy staging uses: shell.run with: command: kubectl apply -f k8s/staging/ - id: integration tests uses: shell.run continue on error: true with: command: pytest tests/integration/ -q - id: deploy production if: ${{ steps.integration tests.output.code == 0 }} uses: shell.run with: command: kubectl apply -f k8s/production/ - id: rollback if: ${{ steps.integration tests.output.code = 0 }} uses: shell.run with: command: kubectl rollout undo deployment/myapp -n staging Documentation overview ¶ documentation-overview | Section | What you'll find | |---|---| | Core Concepts concepts/ How-to Guides how-to/ Built-in Nodes nodes/builtin/ Plugin Development plugins/creating/ CLI Reference cli/reference/ Compatibility ¶ compatibility | Python | 3.10 · 3.11 · 3.12 · 3.13 | | OS | macOS · Linux · Windows WSL | | Storage | SQLite default | | License | MIT |