RelayRunner docs: Keep up with coding agents
Page: https://relayrunner.app/docs/guides/agent-surge
Markdown: https://relayrunner.app/docs/guides/agent-surge.md
All pages: https://relayrunner.app/docs/llms.txt

Other pages (Markdown):
- Changelog: https://relayrunner.app/docs/changelog.md
- CLI changelog: https://relayrunner.app/docs/changelog/cli.md
- CI traces in your observability tool: https://relayrunner.app/docs/changelog/opentelemetry-traces.md
- Platform changelog: https://relayrunner.app/docs/changelog/platform.md
- Retries, queueing and provider usage: https://relayrunner.app/docs/changelog/retries-queueing-and-provider-usage.md
- Optimized checks: https://relayrunner.app/docs/concepts/optimized-checks.md
- Principles: https://relayrunner.app/docs/concepts/principles.md
- Routing: https://relayrunner.app/docs/concepts/routing.md
- Runner order: https://relayrunner.app/docs/concepts/runner-order.md
- Add a provider: https://relayrunner.app/docs/contribute/add-provider.md
- Feedback: https://relayrunner.app/docs/contribute/feedback.md
- Activity and history: https://relayrunner.app/docs/dashboard/activity.md
- Performance: https://relayrunner.app/docs/dashboard/performance.md
- Remove RelayRunner: https://relayrunner.app/docs/dashboard/remove.md
- Signals: https://relayrunner.app/docs/dashboard/signals.md
- Telemetry: https://relayrunner.app/docs/dashboard/telemetry.md
- Usage and savings: https://relayrunner.app/docs/dashboard/usage.md
- Workspaces and members: https://relayrunner.app/docs/dashboard/workspaces.md
- Set up with an agent: https://relayrunner.app/docs/get-started/agents.md
- How it works with GitHub Actions: https://relayrunner.app/docs/get-started/github-actions.md
- Install the CLI: https://relayrunner.app/docs/get-started/install.md
- Move your workflows over: https://relayrunner.app/docs/get-started/move-over.md
- Route GitHub Actions jobs to any runner: https://relayrunner.app/docs/get-started/overview.md
- Quickstart: https://relayrunner.app/docs/get-started/quickstart.md
- Keep up with coding agents: https://relayrunner.app/docs/guides/agent-surge.md (this page)
- Run CI on your laptop while you work: https://relayrunner.app/docs/guides/laptop-ci.md
- macOS and iOS builds on your Mac: https://relayrunner.app/docs/guides/mac-builds.md
- Spend controls: https://relayrunner.app/docs/guides/spend-controls.md
- Share your team's machines: https://relayrunner.app/docs/guides/team-machines.md
- RelayRunner API: https://relayrunner.app/docs/reference/api.md
- CLI: https://relayrunner.app/docs/reference/cli.md
- Errors: https://relayrunner.app/docs/reference/errors.md
- FAQ: https://relayrunner.app/docs/reference/faq.md
- GitHub App: https://relayrunner.app/docs/reference/github-app.md
- Runner labels: https://relayrunner.app/docs/reference/labels.md
- MCP server: https://relayrunner.app/docs/reference/mcp.md
- Data and privacy: https://relayrunner.app/docs/reference/privacy.md
- relay.yml inputs: https://relayrunner.app/docs/reference/relay-inputs.md
- Repo config: https://relayrunner.app/docs/reference/repo-config.md
- Security: https://relayrunner.app/docs/reference/security.md
- Troubleshooting: https://relayrunner.app/docs/reference/troubleshooting.md
- GitHub-hosted: https://relayrunner.app/docs/runners/github.md
- Hosted providers: https://relayrunner.app/docs/runners/hosted.md
- Providers: https://relayrunner.app/docs/runners/providers.md
- Your machines: https://relayrunner.app/docs/runners/self-hosted.md

---

# Keep up with coding agents

> When agents push all day, run CI on your own machines first and burst to hosted runners when they're full.

Coding agents open pull requests around the clock, and each push runs CI. A month's included minutes can go in a few days, a single self-hosted machine turns into a queue, and paying for fast hosted runners for every push adds up quickly.

This guide uses every machine you have first, and sends only the overflow to a hosted provider.

## 1. Connect what you have

Run `relayrunner connect` on every spare computer: the Mac mini, the old laptop, the home server. Each one runs a job or two at once (more with `--concurrency`), so more machines means more jobs at once. Share them with **anyone** in the workspace so jobs from agents and teammates can use them:

```sh
relayrunner share anyone
```

Jobs started by a bot only run on machines shared with anyone.

## 2. Burst to hosted runners

Set the runner order so the overflow goes to a provider instead of waiting:

1. **Self-hosted**
2. **Blacksmith** (optional, if you want faster hosted runners)
3. **GitHub-hosted**

When every machine is busy, the next job goes to the next step straight away, instead of queueing behind the others.

## 3. Cap the hosted spend

Put a minutes limit on GitHub so overflow stops billing at a point you choose. See [Spend controls](/docs/guides/spend-controls). With no unlimited step after it, a job that finds every machine busy fails fast with the reason, and the agent can retry.

## 4. Take the cheap jobs off runners

PR title checks and lint don't need a machine at all. Make them [optimized checks](/docs/concepts/optimized-checks) so they never wait for a runner or bill a minute.

## Watch it

The **Performance** page shows how long each job takes on each runner and how long it waited for one. If waits grow, connect another machine or move a step up.