{"slug": "launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos", "title": "Launch HN: StarSling (YC P25) – Self-improving CI for agent-volume repos", "summary": "StarSling, a YC P25 startup, launched AI-native CI for GitHub Actions that combines drop-in Ubuntu runners with agents that open optimization pull requests for workflows, claiming up to 10x faster CI in its public benchmarks. StarSling says its runners replace ubuntu-latest and ubuntu-24.04 and run up to 33% cheaper than equivalent GitHub-hosted runners, with per-second billing and a one-line workflow change to runs-on: starsling-ubuntu-26.04. The company cites customer results including Mastra's test suite dropping from 29m 56s to 5m 06s wall p95 and Better Auth cutting queue time from 9.5 minutes to 35 seconds.", "body_md": "[Mastra](https://starsling.dev/customers/mastra)\n\n6× Faster test suite\n\n29m 56s → 5m 06s wall p95\n\n“At Mastra we move so fast that the bottleneck becomes reviews and CI. Time spent compounds, and StarSling helps you realize how much time you're losing.”\n\n[Mastra case study](https://starsling.dev/customers/mastra)\n\nUp to 10x faster GitHub Actions runners with AI agents \n\nthat continuously optimize your workflows\n\nNo credit card required\n\nAgents write code faster than CI can check it. These teams made verification keep up.\n\n3M+ CI jobs run\n\n2× Faster E2E\n\n2m 22s → 1m 04s\n\n“We've been using StarSling for Better Auth CI. It's been saving us countless hours, both with fast runners and their agent optimizing our CI.”\n\n16× Shorter queue time\n\n9.5 min → 35 s\n\n“Within a day of migrating to StarSling Runners, their agents opened up a PR that literally made our Rust CI tests 2x faster!”\n\nDrop-in replacement for ubuntu-latest.\n\nInstall in a minute\n\nUpdate your workflow file.\n\n```\njobs:\n  build:\n```\n\n ~~Removed:~~ `runs-on: ubuntu-latest`\n\n Added: `runs-on: starsling-ubuntu-26.04`\n\n```\n    steps:\n      - uses: actions/checkout@v4\n```\n\n| Capability | StarSling | [GitHub-hosted](https://starsling.dev/compare/github-actions) | [Blacksmith](https://starsling.dev/compare/blacksmith) | [Depot](https://starsling.dev/compare/depot) | \n|---|---|---|---|---|\n| [GitHub Actions support](https://starsling.dev/compare#which-runner-fits-which-bottleneck) | Yes | Yes | Yes | Yes | \n| [AI agent PRs](https://starsling.dev/products/runners#agents) | Yes | No | NoRunner right-sizing PRs | No | \n| [Adaptive Compute](https://starsling.dev/blog/adaptive-compute) | Yes | No | No | No | \n| [CI optimization skills](https://starsling.dev/skills) | Yes | No | No | No | \n| Per-second billing | Yes | No | No | Yes | \n\nYour workflow. A faster runner.\n\nEvery job, action and build command stays as written. Switch runners to see the line that changes and the median job time on each.\n\n```\nname: CI\non: [push, pull_request]\n\njobs:\n  build:\nsteps:\n      - uses: actions/checkout@v4\n      - run: npm ci\n      - run: npm test\n```\n\nLatest[Introducing Adaptive Compute: up to 2.3x faster GitHub Actions](https://starsling.dev/blog/adaptive-compute)\n\n[Sandbox Router](https://starsling.dev/blog/adaptive-compute#sandbox-router) sends every job to the fastest available sandbox, and [Afterburner](https://starsling.dev/blog/adaptive-compute#afterburner) adds up to 25% more CPU and up to 50% more RAM to a running step at no extra cost. Up to 2.32x faster than GitHub-hosted runners.\n\nOpen source, one install, and they run on your machine: each skill reads your workflows and hands your coding agent the evidence to fix them.\n\n33% cheaper than GitHub Actions\n\nVolume discounts available\n\nEverything you need to evaluate StarSling for your CI.\n\nStarSling is AI-native CI for GitHub Actions: drop-in Ubuntu runners plus agents that open optimization PRs for your workflows. The runners replace ubuntu-latest and ubuntu-24.04 and run up to 33% cheaper than equivalent GitHub-hosted runners. Together with agent PRs, they made GitHub Actions up to 10x faster in [public benchmarks](https://github.com/starsling-demo-org), and the agents continuously analyze your workflows to keep the pipeline improving.\n\nAgent-native CI is CI that improves itself. Beyond running your workflows on faster hardware, AI agents continuously analyze your jobs, run logs, and machine telemetry, then open pull requests that optimize your pipeline: caching, parallelization, dependency installs, test sharding, and workflow structure. Traditional CI is static; agent-native CI gets faster the longer you use it. Read more about [AI-native CI](https://starsling.dev/ai-native-ci).\n\nTwo things move the needle: faster hardware and removing redundant work. Swap `ubuntu-latest` for a runner with stronger CPUs, then let AI agents find dead steps, cache fixes, and parallelization opportunities your team hasn't had time to fix (in StarSling's [public benchmarks](https://github.com/starsling-demo-org), runners plus agent PRs made CI up to 10x faster). For a deeper guide, read [fast GitHub Actions](https://starsling.dev/fast-github-actions). You can also work through the [GitHub Actions CI best practices](https://starsling.dev/best-practices/github-actions) yourself, without StarSling, or follow [Levels of CI](https://starsling.dev/blog/levels-of-ci) for every way to make GitHub Actions cheaper and faster.\n\nUsually the runner. GitHub-hosted `ubuntu-latest` runs on older shared hardware, so even simple builds spend time waiting on CPU. Switching to faster CPUs (StarSling Runners use 5th Gen AMD EPYC) typically cuts wall-clock time significantly before any workflow optimization.\n\nYes. Change `runs-on: ubuntu-latest` to `runs-on: starsling-ubuntu-26.04` (or `ubuntu-24.04` to `starsling-ubuntu-24.04`) in your GitHub Actions workflow files. No other config changes required. See [StarSling vs GitHub Actions](https://starsling.dev/compare/github-actions) and [GitHub Actions alternatives](https://starsling.dev/github-actions-alternatives).\n\nStarSling is not a full replacement for GitHub Actions. It is a GitHub Actions runner alternative for supported Ubuntu/Linux jobs: you keep GitHub Actions workflows and change the runner label. If you are comparing full CI/CD platforms, read [GitHub Actions alternatives](https://starsling.dev/github-actions-alternatives).\n\n$0.008 per minute for 4 vCPU Linux runners with 16 GB RAM, 33% cheaper than GitHub Actions' $0.012/min. New paid subscriptions are billed by the second, with no one-minute minimum. Queue time is never billed. New accounts get 2,000 free minutes in their first month. See [StarSling pricing](https://starsling.dev/pricing).\n\nYes. [StarSling Disks](https://docs.starsling.dev/runners/disks) are persistent directories mounted into StarSling Runners, so dependency stores and build output, such as pnpm's store or Rust's `target/`, are already in place when the next job starts. In a [benchmark](https://github.com/starslingdev/disks#performance-comparison) on Mastra's 4.5 GiB pnpm store, dependencies were ready in about 25 seconds, 4.5x faster than GitHub's `actions/cache`. Pull requests from the same repository read the default branch's published disk. Storage is $0.50 per GB-month.\n\nStarSling Runners are x64 Linux, from 2 to 64 vCPU. Need ARM? Email [founders@starsling.dev](mailto:founders@starsling.dev).\n\nBuilding Docker images in CI? Email [founders@starsling.dev](mailto:founders@starsling.dev) to talk through caching layers on StarSling Runners.\n\nYes. StarSling GPU Runners are drop-in GitHub Actions runners backed by a dedicated NVIDIA GPU: RTX PRO 6000 at a normalized $0.06422 per minute, RTX 5090 at $0.03022, and RTX 4090 at $0.02522, with H100 coming soon. Set `runs-on: starsling-ubuntu-26.04-gpu` and pick a card in the label. The GPU is dedicated to that job for as long as it runs, so nothing reclaims it partway through your suite. [Explore StarSling GPU Runners](https://starsling.dev/products/gpu-runners).\n\nRTX PRO 6000 is the default, and it suits large-model and memory-heavy CI workloads. RTX 5090 suits fast inference tests and model evals. RTX 4090 covers everyday GPU tests at the lowest per-minute cost. You choose per job in the `runs-on:` label, so different jobs in the same workflow can use different cards. [Explore StarSling GPU Runners](https://starsling.dev/products/gpu-runners).\n\nYes. StarSling Review Runners are code review agents you configure and run in your own CI. One workflow file, and every pull request is analyzed as a GitHub Actions job on a StarSling runner using your model key, review skills and scripts from your codebase, and team-defined reviewers. Skills and instructions load from the trusted base branch, so a pull request cannot rewrite its own reviewer. The output is a review comment on the pull request, before a human opens it. [Explore StarSling Review Runners](https://starsling.dev/products/review-runners).\n\nA review is a GitHub Actions job on a StarSling runner in the same account as the rest of your CI. It runs on starsling-review, a 4 vCPU runner with 16 GB of memory. Review Runner time has a normalized rate of $0.004 per minute. New paid subscriptions are billed in whole seconds from job start to finish. Partial seconds round up, with no one-minute minimum. Existing paid subscriptions remain billed in whole minutes with a one-minute minimum until migrated. Queue time is never billed. Concurrency is unlimited. Model tokens are billed by your own provider, on the account you already have. [Explore StarSling Review Runners](https://starsling.dev/products/review-runners).\n\nAfter installing the StarSling GitHub App, AI agents continuously analyze your workflows, jobs, run logs, and machine telemetry, then open pull requests that optimize your setup: cache fixes, faster install strategies, Docker health checks, test sharding, parallelization, workflow structure, and job ordering. You review and merge. Optimization PRs are on paid plans, off by default for new accounts.\n\nCoding agents (Claude Code, Cursor, Codex) push PR volume up several-fold, which compounds CI cost and queue times fast. The right fit is a runner with unlimited concurrency, continuous AI optimization (so the pipeline gets faster as PR volume grows), and per-minute pricing with no seat fees. StarSling Runners are built for this pattern.\n\nFailed jobs are billed for the time they run: whole seconds on new paid subscriptions, with partial seconds rounded up; whole minutes on existing paid subscriptions until migrated. Queue time is never billed. New accounts get 2,000 free minutes in their first month.\n\nEach job runs in its own single-use, hardware-isolated microVM that's destroyed after the run. That's the same isolation model GitHub-hosted runners use, so there's nothing for a later job or a fork PR to persist on or reach. Secrets pass directly from GitHub to your job and are never stored by StarSling. More details in [our docs](https://docs.starsling.dev/security/data-handling).\n\nSign up with GitHub and install the StarSling GitHub App, switch runners with one line, and run 2x faster on day one. StarSling agents keep finding the next speedup.", "url": "https://wpnews.pro/news/launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos", "canonical_source": "https://starsling.dev", "published_at": "2026-11-17 19:01:43+00:00", "updated_at": "2026-11-17 20:17:33.194550+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-tools"], "entities": ["StarSling", "Y Combinator", "GitHub Actions", "Mastra", "Better Auth", "Blacksmith", "Depot"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos", "markdown": "https://wpnews.pro/news/launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos.md", "text": "https://wpnews.pro/news/launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos.txt", "jsonld": "https://wpnews.pro/news/launch-hn-starsling-yc-p25-self-improving-ci-for-agent-volume-repos.jsonld"}}