agent.cloud
Build with any agent

Your agents build the apps. We keep them running.

Use the agent you already have. agent.cloud runs the app, rehearses risky releases on a branch of production, and asks you before the first release and before your data changes.

Works with the agent you already use
  • Claude Code
  • Cursor
  • Codex
  • GitHub Copilot
  • Gemini CLI
  • Windsurf
  • Cline
  • Zed
  • OpenCode
  • Warp
  • Aider
  • Amp
  • Goose
  • and anything with a terminal
Your app, ticketNO. 1016
Or start from one
Paste into your agentRuns on your laptop
Read https://agent.cloud/agents.md, then build this and run it on my laptop: a revenue dashboard that emails my team a summary every morning, with yesterday against plan.
How a release ships

Your agent moves fast.
Production stays calm.

  1. agc up · done

    Work on a mirror

    Your agent works on a masked mirror of production, on localhost: real shapes, no real people.

  2. agc ship · skippedrehearsedcheck failed

    Rehearse the release

    Releases with checks, database changes or a worker run first on a fresh branch of production. If a check fails, production keeps what was live.

  3. your OK · skippedapproved in the sessionnot reached

    A person decides

    The first release and every database change wait for you. Code-only releases go on their own.

  4. live · donekept v6

    Live, and on record

    Every live release is a commit in the app's private GitHub repo, and production is watched every minute.

Release receiptrcp_7f3a…rcp_b21e…rcp_9c04…
campfire v6v7
Live
Stopped
Command
agc ship -m "Waitlist offersWaitlist tableFaster checkout"
State
LiveStopped
mirrordone
rehearseskippeddonefailed
your OKskippeddone—
livedone—
A person needed?No

Code only, and this app lets agents release code on their own.

A person needed?Yes

A database change, rehearsed first. Approved by rc, in the session.

Check failed in the rehearsal
never overbooked: 1 violation.

Production keeps serving v6.

Held: this check stopped a bad release. Changing it needs a person.
On recordCommit + watched every minuteProduction kept v6
When something breaks

Problems arrive with fixes.

  1. sentinel · every minute

    It notices first.

    Server errors, slow responses, crashes and new kinds of error open an incident, often before anyone reports it.

  2. agc capsule

    Your agent sees what happened.

    The failed requests, the error, where in the code, and the releases around it. No logs pasted into chat.

  3. agc up · at 14:02

    Production, as it was.

    A masked copy of production from that moment, on the agent's machine. Real shapes, no real people.

  4. agc ship · fix

    The fix comes with a check.

    The agent adds a check that fails without the fix, and ships them together through the same rehearsal.

  5. held

    And stays fixed.

    That check is held: no agent can weaken or remove it without a person.

Incident ticketinc_4k2…
campfire
Fixed

500s on POST /api/bookings since v6

noticeddone
understooddone
reproduceddone
fixeddone
On recordFixed in v8 · check held
Your stack

TypeScript or Python.
No Dockerfile.

TypeScript, end to end

A React and Vite UI, one Node 24 server, Postgres through DATABASE_URL, and migrations as plain SQL files. agent.cloud builds it with npm.

agentcloud.tomlchecks
[[check.invariant]]   # SQL that must return no rows
name = "never overbooked"
sql  = "SELECT c.id FROM camps c JOIN bookings b ON b.camp_id = c.id AND b.status = 'confirmed' GROUP BY c.id, c.capacity HAVING count(*) > c.capacity"

[[check.smoke]]       # HTTP steps, in order
name  = "twenty parents race for the last spot"
steps = [
  "POST /api/camps {name: 'Race {run}', capacity: 1} -> 201 as camp",
  "POST /api/camps/{camp.id}/bookings {email: 'p{i}@example.test'} -> 201|409 x20",
]

Every release with a worker is rehearsed twice: once calm, once while we kill the worker mid-job. And no existing row may disappear in a migration.

Yours to keep

Your code on GitHub

Every release is a commit in a private repo. Take it to your own GitHub any time.

Run

Production, explained

Requests, server errors and p95 response time per release, for you. Your agent gets the incident and what happened.

The agent.cloud cloud, with a glass of milk and a laptop

Got an idea? Ship it today.

Your prompt builds

A revenue dashboard that emails my team a summary every morning, with yesterday against plan

Change the idea