GitHub Actions vs Buildkite

GitHub Actions is the CI built into GitHub: workflows in your repository run as jobs on fresh VMs that end within 6 hours. Buildkite is a separate CI platform whose hosted agents run each pipeline job for up to 8 hours on Linux in a VM that is destroyed after, with cache volumes to carry chosen paths forward.

The companies and products

GitHub Actions

GitHub Actions is GitHub's CI/CD service: workflows in your repository run as jobs on runners that GitHub hosts or that you host yourself.

GitHub Actions is a CI service, not a general sandbox API. Each job on a GitHub-hosted runner gets a new VM with passwordless sudo, and GitHub removes the VM when the job ends. Windows and larger runners run on Azure, standard Linux runners run on a multi-cloud pool, and macOS runs on GitHub's own Mac fleet. The 1-CPU slim runner is a container, not a VM. Actions is built to build, test and deploy the code in a repository. The Copilot cloud agent runs on Actions runners when you start it from the web or Copilot Chat. The newer Copilot in the cloud runs in a Copilot cloud sandbox by default: an isolated Linux session that keeps a snapshot when it stops.

Buildkite

Buildkite is a CI and software delivery platform, and hosted agents are the build machines it runs for you.

You write Buildkite pipelines, and each job runs on a new virtual machine that Buildkite starts for that job and destroys when it ends. Cache volumes and custom agent images carry files and packages to the next job. Hosted agents run Linux (AMD64 and ARM64) and macOS on Apple M4, and Windows is in public preview. You can also run Buildkite's agent on your own machines. It is a CI service, not an agent sandbox, so this page compares the part where they overlap: a machine where an agent or a job does its work.

Which use cases each one fits

For each use case, Battleships prices every sandbox provider on the same workload and sorts them from the cheapest monthly bill up. “85th cheapest of 374” means 84 of the other 373 providers run that workload, with every feature it needs, for less. “With limits” means the provider runs it but misses something, so it is listed after every full match. Open a use case for its whole ranking and what each provider misses.

Use case and its workloadGitHub Actions: price rankBuildkite: price rankboat: price rank
Software factory
100 at once · 4 vCPU / 8 GB · 2,200 sessions of 8 h a month
A software factory needs agents that keep their checkout and Docker cache between tasks. On GitHub Actions you restore them from the cache, artifacts or a larger-runner custom image, and on Buildkite from cache volume paths or a custom agent image. boat keeps the whole disk and ranks #5 in our preset.
304th of 365, with limits
$5,553 a month
81st of 365, with limits
$11,648 a month
5th cheapest of 365
$634 a month
Always-on AI employees
50 machines 24/7 · 2 vCPU / 4 GB
An assistant that lives on its machine all month fits neither CI service, since jobs stop after 6 hours on GitHub Actions and 8 on Buildkite (longer on request). On boat, turn auto-stop off on a paid plan; there is then no session cap.
151st of 361, with limits
$12,882 a month
349th of 361, with limits
$17,564 a month
6th cheapest of 361
$657 a month
Code interpreter bursts
100 at once · 1 vCPU / 2 GB · 200,000 sessions of 1 min a month
288th of 336, with limits
$721 a month
309th of 336, with limits
$1,587 a month
189th of 336, with limits
$2,000 a month
Sandboxes for your users
300 at once · 2 vCPU / 4 GB · 30,000 sessions of 23 min a month
Neither takes public inbound traffic for your users, and GitHub's terms rule out offering Actions as a service. boat gives each sandbox HTTPS on up to 50 ports, token-gated by default, and ranks #3 in our preset.
302nd of 349, with limits
$2,892 a month
320th of 349, with limits
$4,984 a month
3rd cheapest of 349
$209 a month
RL rollouts
1,000 at once · 2 vCPU / 4 GB · 1,000,000 sessions of 3 min a month
297th of 349, with limits
$14,721 a month
310th of 349, with limits
$23,881 a month
39th of 349, with limits
$2,000 a month
Agent evals
250 at once · 4 vCPU / 8 GB · 15,000 sessions of 20 min a month
299th of 359, with limits
$1,662 a month
322nd of 359, with limits
$3,884 a month
10th cheapest of 359
$200 a month
CI runners
40 at once · 8 vCPU / 16 GB · 6,000 sessions of 12 min a month
Both are built for CI: GitHub Actions fits a GitHub repository with no extra service (#85 in our CI preset), and Buildkite brings its own pipelines and cache volumes (#202, held by its 256 vCPU Pro pool). boat ranks #2; it runs CI jobs on full VMs that keep a warm disk, but has no pipeline service.
85th cheapest of 374
$729 a month
202nd of 374, with limits
$2,318 a month
2nd cheapest of 374
$86 a month
24/7 dev boxes
1 machine 24/7 · 4 vCPU / 8 GB
A dev box needs SSH, open ports and a disk that stays. On GitHub runners you add SSH with a third-party action inside a job; Buildkite offers a terminal into a running job. boat keeps the disk for at least 14 days after a stop; its IP changes at each resume.
253rd of 371, with limits
$71 a month
357th of 371, with limits
$715 a month
19th cheapest of 371
$26 a month
Computer-use agents
50 at once · 4 vCPU / 8 GB · 20,000 sessions of 15 min a month
GitHub runners have no desktop stream (you set up Xvfb yourself), and Buildkite's macOS desktop access is for a person debugging a job. boat streams a 1920x1080, 60 fps Linux desktop with computer tools.
306th of 367, with limits
$1,502 a month
119th of 367, with limits
$3,500 a month
7th cheapest of 367
$200 a month
Browser-use agents
50 at once · 2 vCPU / 4 GB · 30,000 sessions of 10 min a month
198th of 356, with limits
$942 a month
210th of 356, with limits
$1,772 a month
7th cheapest of 356
$200 a month
Scraping & bots (startup scale)
50 at once · 1 vCPU / 2 GB · 100,000 sessions of 3 min a month
202nd of 343, with limits
$1,184 a month
216th of 343, with limits
$2,354 a month
6th cheapest of 343
$90 a month
Mass scraping & bots (undetectable)
1,000 at once · 1 vCPU / 2 GB · 3,000,000 sessions of 2 min a month
296th of 327, with limits
$28,971 a month
313th of 327, with limits
$46,814 a month
73rd of 327, with limits
$1,800 a month
Parallel red teaming
200 at once · 2 vCPU / 4 GB · 5,000 sessions of 30 min a month
123rd of 351, with limits
$467 a month
143rd of 351, with limits
$1,184 a month
3rd cheapest of 351
$200 a month
GPU eval jobs
10 at once · 8 vCPU / 32 GB · 500 sessions of 30 min a month
GitHub Actions offers NVIDIA T4 larger runners. Buildkite's hosted shapes and boat's sizes are CPU only.
Not ranked: misses a requirementNot ranked: misses a requirementNot ranked: misses a requirement
macOS agents
5 at once · 4 vCPU / 8 GB · 1,000 sessions of 20 min a month
Both host macOS: GitHub on Apple silicon and Intel (#23 in our preset), Buildkite on Apple M4 with current Xcode (#34). boat runs Linux only.
23rd of 35, with limits
$1,178 a month
34th of 35, with limits
$2,310 a month
Not ranked: misses a requirement

Key features

FeatureGitHub ActionsBuildkiteboat
Kind of productCI built into GitHub: jobs run from workflow files in a repositorySeparate CI platform: hosted agents run jobs from Buildkite pipelinesSandbox API: create, stop, fork and reach full VMs from your code
IsolationNew VM per job with passwordless sudo; Windows and larger runners on Azure, standard Linux on a multi-cloud pool, macOS on GitHub's Mac fleetA VM per job, destroyed with its data after; Apple Virtualization framework on macOSFull VM with its own kernel, root and systemd, on a physical host dedicated to boat; vCPUs are shared, not dedicated cores
How long a job or machine runsUp to 6 hours per jobUp to 8 hours per job on Linux and 4 on macOS, longer on requestAuto-stop defaults to 1 hour; set up to 30 days, or turn it off on a paid plan for no session cap
Files between runsEach job starts on a fresh VM. You set it up: carry files through the cache or artifacts, or save a larger runner's disk as a custom image with the `snapshot` keywordThe VM is destroyed. You set up what carries over: cache volume paths, saved after successful jobs, best effort, up to 14 days; or packages baked into a custom agent imageThe whole disk is saved every minute and at each stop, kept at least 14 days after a stop; memory, /tmp and some caches are not saved
ForkNo live fork; a larger-runner job can save its disk as a custom image when it completes, and new jobs start from that imageEach job gets its own copy of the last committed cache volumeFork a running sandbox in one call, from its last 1-minute snapshot
Docker and nested virtualizationDocker, and KVM on Linux runners (including 2-vCPU ones) after you add the runner user to the KVM groupDocker on Linux; macOS has the Docker CLI, and you connect a daemon you provide; /dev/kvm not documentedDocker, root, systemd and /dev/kvm on every sandbox
Reaching the machineNo public inbound access; runners joined to your Azure network can be reached only from inside that networkNo inbound ports documented; a terminal into a running job through Buildkite's UI or bk job ssh; for a URL, you set up an outbound tunnel yourselfSSH and up to 50 HTTPS URLs, token-gated by default; public IPv6 or IPv4 that changes at each resume; some sandboxes have no IPv4 of their own
Desktop and computer useNo desktop stream; browsers are preinstalled for tests. You set it up: a virtual display such as Xvfb for screenshots and recordingsBrowser-based desktop access for a person who debugs a running macOS job; no computer-use API documented1920x1080, 60 fps Linux desktop with Chrome and computer tools
Coding agentsCopilot cloud agent, plus Claude and Codex in public preview, working on issues and pull requests; a REST API in public preview starts Copilot tasksYou set it up: install Claude Code in a custom agent image or a step, and run it as a pipeline jobSeven harnesses preinstalled (Claude Code, Codex and more), driven from outside with a prompt, steer and events API
Keeping API keys outSecrets enter the job as inputs or environment variables and are hidden from logs; OIDC gives short-lived cloud tokensAnthropic proxy: jobs call it with the job token and Buildkite sets the API key header; other secrets enter the jobOptional paid credentials proxy ($1 per day on, plus $1 per 1,000 requests) for supported AI providers; other secrets still enter the sandbox
Operating systemsLinux x64 and arm64, Windows x64 and arm64, macOSLinux AMD64 and ARM64, macOS on Apple M4, Windows Server 2022 in public previewUbuntu 24.04 on x86_64 only; Windows programs through Wine
GPUsLinux and Windows larger runners with an NVIDIA T4CPU onlyNo GPU on any size
Biggest machineLarger runners in several sizes, billed at their own ratesLinux up to 8 vCPU / 32 GB on Pro and 64 vCPU / 256 GB on Enterprise; macOS up to 12 vCPU / 56 GBUp to 16 vCPU / 32 GB (xlarge) on the $100 plan and above
RegionsLarger runners can get static IP ranges or join your Azure private network in the US, Europe and APAC; standard Linux runners use a multi-cloud poolUS East Coast data centers; no region choiceGermany, Finland and France; no region choice, and snapshot copies can be stored outside the EU
Every feature Battleships tracks (43)
FeatureGitHub ActionsBuildkiteboat
Full VM (own kernel)YesYesYes
Docker insideYesYesYes
Nested virtualizationYesNo documented wayYes
RootYesNot publishedYes
SystemdNo documented wayNo documented wayYes
Desktop GUINo documented wayYesYes
BrowserYesYesYes
Computer-use APINo documented wayNo documented wayYes
SSHNo documented wayYesYes
Persistent diskNo documented wayYesYes
Pause/resumeNo documented wayNo documented wayYes
Automatic snapshotsNo documented wayYesYes
Fork/cloneNo documented wayYesYes
Live fork (no pause)No documented wayNo documented wayYes
Memory forkNo documented wayNo documented wayNo documented way
Custom image (Docker or snapshot)YesYesYes
≥24 h sessionsNo documented wayNo documented wayYes
Idle auto-stopYesYesNo documented way
Wake on requestNo documented wayNo documented wayNo documented way
HTTPS preview URLsNo documented wayNo documented wayYes
Raw TCP inboundNo documented wayNo documented wayYes
Public IPv4No documented wayNo documented wayNo documented way
Egress allowlistYesNo documented wayNo documented way
Secret proxyNo documented wayYesYes
Secret proxy for any APINo documented wayNo documented wayYes
Preinstalled agentsYesNo documented wayYes
Agent harness APIYesNo documented wayYes
MCP serverYesYesNo documented way
GPUYesNo documented wayNo documented way
WindowsYesYesNo documented way
Arm64YesYesNo documented way
Self-hostingYesYesNo documented way
BYOCNo documented wayNo documented wayNo documented way
Open sourceYesNo documented wayNo documented way
Scoped API keysNot publishedNot publishedYes
Spend limitsYesNot publishedYes
Usage per sandbox (API)YesNo documented wayYes
Audit logsYesNot publishedNo documented way
SSOYesYesNo documented way
SOC 2YesYesNo documented way
HIPAANo documented wayNo documented wayNo documented way
EU data residencyYesNo documented wayNo documented way
Zero data retentionNot publishedNot publishedYes

Performance

GitHub ActionsNot measured
BuildkiteNot measured
boat28.06 runs/s

Neither GitHub Actions hosted runners nor Buildkite hosted agents are in the public benchmarks we use, so we cannot say which is faster. For reference, boat did 28.06 runs per second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB, second of 15 in StarSling's run of 3 October 2026 (run 37073680030). That boat sandbox ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure.

V8 Web Tooling Benchmark at a 4 vCPU / 8 GB target, runs per second, higher is better. Source: StarSling's run of 3 October 2026 (run 37073680030), median of 5 sandboxes. Providers ran on different hardware in different regions. StarSling gives a shared rank when the run cannot separate two providers. Every boat sandbox in this run ran on an AMD Ryzen 9 9950X host. boat also places some sandboxes on AMD Ryzen 7 9700X hosts, which this run did not measure. GitHub Actions and Buildkite are not in the public benchmarks we use, so we cannot say which is faster.

Pricing in five scenarios

Each bill is priced from the providers' public price lists by the open Battleships engine, with the cheapest plan that runs the scenario. Start limits, per-start fees and plan minimums are in the price, boat's included.

ScenarioGitHub Actions, a monthBuildkite, a monthboat, a month
One coding agent, workdays
4 vCPU / 8 GB, 50 GB disk, 8 hours a day, 22 days a month, files kept between days
$21 · Enterprise Cloud · with limits$166 · Pro · with limits$20 · $20/mo
One agent that never stops
4 vCPU / 8 GB, 50 GB disk, running 24/7 all month
$71 · Enterprise Cloud · with limits$715 · Pro · with limits$26 · $20/mo
50 agents in parallel
50 machines of 4 vCPU / 8 GB at once, 8-hour sessions, 1,100 sessions a month, Docker inside
$3,565 · Enterprise Cloud · with limits$7,677 · Pro · with limits$317 · $20/mo × 3 seats
Sandboxes for your users
2 vCPU / 4 GB, 30,000 sessions of 10 minutes a month, up to 300 at once
$1,092 · Enterprise Cloud · with limits$2,204 · Pro · with limits$200 · $100/mo × 2 seats
1,000 short jobs at once
2 vCPU / 4 GB, 1,000 at once, 3 minutes each, 200,000 jobs a month
$2,721 · Enterprise Cloud · with limits$4,787 · Pro · with limits$8,800 · $2000/mo · with limits

GitHub Actions: GitHub bills per minute per job, rounding each job up to the next whole minute, at a rate set by the runner type, from $0.006 a minute for 2-core Linux. Each plan includes a monthly compute amount in dollars ($12 Free, $18 Pro and Team, $300 Enterprise Cloud), shared with Copilot cloud sandboxes. It covers standard runners, and larger runners can draw from it on Team and Enterprise. Public repositories use standard runners for free.

Buildkite: Buildkite Pro costs $30 per active user a month and includes 4,000 Linux AMD64 vCPU minutes. After that, Linux (AMD64 and ARM64) is $0.004 per vCPU minute, Windows $0.008 and macOS $0.02, metered to the second with no minimums. Pro shares pools of 256 Linux AMD64 vCPU, 64 ARM64 vCPU and 48 macOS vCPU across running agents. Enterprise pricing is custom.

Buildkite: Plans cost $20, $100, $500 or $2,000 a month, and the whole plan price comes back as VM time for that month. A 4 vCPU / 8 GB sandbox costs $0.036 an hour, billed per second while it runs. The $20 plan includes 100 sandboxes at once and 12 starts a minute, 60 an hour and 200 a day; extra starts cost $0.03 to $0.07. A stopped sandbox has no compute charge and keeps its disk for at least 14 days; saved snapshots above the included count and the credentials proxy still charge.

Limits in those scenarios

Neither CI service fits the agent scenarios as a sandbox: GitHub Actions jobs end after 6 hours, and Buildkite jobs after 8, with only cached paths, cache volumes or custom images kept. For 1,000 short jobs at once, GitHub Enterprise standard runners stop at 500 concurrent jobs, larger runners on Team and Enterprise allow 1,000, and Buildkite Pro shares one pool of 256 Linux vCPU, so jobs above it wait in the queue. On boat the limit is 100 to 2,000 sandboxes at once by plan, plus starts. The burst does not fit boat either: the $2,000 plan includes 90 starts a minute and 2,400 a day, extra starts cost $0.03 to $0.07, starts above 270 a minute fail with 429, and boat never queues a start. Auto-stop defaults to 1 hour, and a machine failure loses what was written after the last good snapshot.

ScenarioGitHub ActionsBuildkiteboat
One coding agent, workdays
  • Enterprise Cloud: sessions capped at 6 h
  • different kind of product: CI runner
  • different kind of product: CI runner
  • files survive a stop only in cache volume paths: packages installed elsewhere reset
  • egress price not published
None for this scenario
One agent that never stops
  • Enterprise Cloud: sessions capped at 6 h
  • different kind of product: CI runner
  • different kind of product: CI runner
  • sessions end after 8 h: needs restarts to run 24/7
  • files survive a stop only in cache volume paths: packages installed elsewhere reset
  • egress price not published
None for this scenario
50 agents in parallel
  • Enterprise Cloud: sessions capped at 6 h
  • different kind of product: CI runner
  • different kind of product: CI runner
  • files survive a stop only in cache volume paths: packages installed elsewhere reset
  • egress price not published
None for this scenario
Sandboxes for your users
  • different kind of product: CI runner
  • Pro: max 128 concurrent
  • Pro: max 256 vCPU running at once (needs 600)
  • different kind of product: CI runner
  • egress price not published
None for this scenario
1,000 short jobs at once
  • Enterprise Cloud: max 500 concurrent
  • different kind of product: CI runner
  • needs talk to sales: above plan "Enterprise Cloud" limits: contact sales for more
  • Pro: max 128 concurrent
  • Pro: max 256 vCPU running at once (needs 2,000)
  • different kind of product: CI runner
  • egress price not published
  • 2,400 starts/day included, paid above that (needs ~6,667)
  • 600 starts/hour included, paid above that (needs ~1,000)
  • starts above 90/min are paid, and starts above 270/min fail with 429

Which one should you use?

Use GitHub Actions when

your code is on GitHub and you want CI right inside it, or you need Windows, arm64, macOS or a T4 GPU, or the Copilot, Claude or Codex agents on your pull requests.

  • Already in your GitHub repo. If your code lives on GitHub, Actions runs from pushes and pull requests with no second service to sign up for or wire up.
  • More platforms, including GPUs. Teams that need Windows on arm64, Intel macOS or an NVIDIA T4 GPU get hosted runners for each.
  • Included usage and your own network. Public repos use standard runners free, every plan includes monthly compute usage ($12 on Free), and larger runners can join your Azure network outside the US.

Use Buildkite when

you want a dedicated CI platform with its own pipelines, jobs longer than 6 hours, cache volumes, macOS on Apple M4, or Linux build machines up to 64 vCPU.

  • Longer jobs. Builds that run past 6 hours fit: Buildkite Linux jobs go up to 8 hours, and support can allow longer.
  • Files that carry forward. Cache volumes keep chosen paths, such as a dependency or Git cache, for the next job without uploading them as artifacts.
  • Big Linux machines and per-second billing. Heavy builds can use up to 64 vCPU and 256 GB on Enterprise, in AMD64 and ARM64, billed per second with no minimum per job.

Where boat fits

GitHub Actions and Buildkite are both CI services: each job gets a fresh machine that is thrown away when it ends. If what you run is agents that work for hours or days, keep their files, serve a preview or need a desktop, look at boat. It is not a CI service, but it gives each agent one full Linux VM that keeps its disk.

A machine that keeps its state

Jobs end after 6 hours on GitHub Actions and 8 on Buildkite, and each starts clean apart from caches, cache volumes or custom images. boat saves the whole disk every minute and at each stop; turn auto-stop off on a paid plan for no session cap. Memory and running programs are not saved.

Reachable from outside

Neither CI service documents public inbound connections, so a preview server or webhook needs a tunnel you set up inside the job. boat gives each sandbox SSH and HTTPS URLs on up to 50 ports.

Agents driven from outside

On both, an agent is a job you start and read through logs. Secrets sit inside the VM, or on Buildkite go through its Anthropic proxy. boat lets you prompt and steer seven preinstalled agent harnesses by API, and its optional paid proxy covers the supported AI providers.

Use boat when what you run is agents on Linux for hours or days: one full VM that keeps its disk, Docker and /dev/kvm, a 60 fps desktop, HTTPS URLs and coding agents you drive from outside. Check that its EU-only hosts, x86_64 Linux and start limits fit your work. Compare it one to one: boat vs GitHub Actions and boat vs Buildkite.

boat's own limits
  • Plans start at $20 a month. The plan price comes back as VM time for that month. Unused time does not carry over. Source
  • Starts (create, fork, resume): the $20 plan includes 12 a minute, 60 an hour and 200 a day. The $2,000 plan includes 90 a minute, 600 an hour and 2,400 a day. Extra starts cost $0.03 to $0.07. A start fails with 429 above 3 times the included starts per minute, or 6 times per hour or per day. Source
  • A stopped sandbox has no compute charge. boat keeps its disk for at least 14 days. A saved snapshot keeps it longer; extra saved snapshots and the AI credentials proxy are paid. Source
  • Auto-stop defaults to 1 hour. You can turn it off on a paid plan. The trial allows 2 hours at most. Source
  • boat saves the disk every minute and at each stop. Memory, running programs and /tmp are not saved: a resume is like a reboot. A machine failure loses writes after the last good snapshot. Source
  • Machines run in Germany, Finland and France only. Snapshot copies can be stored outside the EU. Source
  • Public IPv6 and outbound IPv4. No dedicated IPv4. The IP changes at each resume. Source
  • Hosts are AMD Ryzen 7 9700X and Ryzen 9 9950X. vCPUs are shared. No GPU. You cannot boot your own Docker image. Source

Questions people ask

Is GitHub Actions cheaper than Buildkite?

In the scenarios we priced, GitHub Actions came out lower: one agent on workdays is $21 a month on GitHub's 4-core arm64 runners and $166 on Buildkite, one agent all month $71 against $715, and 50 agents in parallel $3,565 against $7,677. Neither fits those agent scenarios, because jobs end after 6 or 8 hours. boat came to $20, $26 and $317 for the same three. Buildkite's 4 vCPU shape has 16 GB of RAM, boat's has 8 GB.

Which is faster, GitHub Actions or Buildkite?

Neither is in the public benchmarks we use, so we cannot say. For reference, boat did 28.06 runs per second on the V8 Web Tooling Benchmark at 4 vCPU / 8 GB in StarSling's run of 3 October 2026, on an AMD Ryzen 9 9950X host.

How long can a job run on each?

GitHub-hosted runners stop a job after 6 hours. Buildkite hosted agents allow up to 8 hours on Linux and 4 on macOS, and support can allow longer runs. A boat sandbox auto-stops after 1 hour by default; you can set up to 30 days, or turn auto-stop off on a paid plan for no session cap.

Do files persist between jobs?

On GitHub Actions each job starts on a new VM; you carry files through the cache, artifacts or a larger runner's custom image. On Buildkite, paths you declare as cache volumes are saved after successful jobs, best effort, for up to 14 days, and packages can go in a custom agent image. boat saves the whole disk every minute and at each stop, and keeps a stopped sandbox's disk for at least 14 days; memory, /tmp and some caches are not saved.

Can GitHub Actions and Buildkite run Docker and Android emulators?

Both run Docker on Linux. GitHub Linux runners expose KVM for Android emulators once you add the runner user to the KVM group, while Buildkite does not document /dev/kvm. boat has Docker and /dev/kvm on every sandbox.

Can I run AI coding agents on them?

Yes, as CI jobs: GitHub runs its Copilot cloud agent and Claude and Codex on Actions runners, and on Buildkite you install Claude Code in a step and call its Anthropic proxy. The agent stops when the job ends. On boat seven agent harnesses are preinstalled, and you prompt and steer them by API.

Try boat

Install the CLI, then run boat new.

7-day free trial

More comparisons