use-cases / wake-agent-at-3am / hero

Cron · Agent · Containers

Wake an agent at 3am, retire it at 4

A nightly job that scans yesterday's billing exceptions, clusters duplicates and writes a triage note. It only needs to exist for about an hour a day. Two cron entries spin a fresh agent container up at 02:59 and tear it down at 04:01. The other 23 hours, it is not running, not warm, not billed.

Read the docs

admin.containers.hoody.com

https://admin.containers.hoody.com/agents/lifecycle?since=last-weekIdle now

billing-reconcileidle · 0 procs

UTC

Last 24 hours

00:0006:0012:0018:0023:59

Alive 02:59 → 04:01

Last 7 days · alive cells

MON

TUE

WED

THU

FRI

SAT

SUN

This week

7h7h alive · server bill unchanged

MON62m alive
TUE60m alive
WED58m alive
THU61m alive
FRI60m alive
SAT59m alive
SUN60m alive
Total alive420m

One agent. One hour a night. Idle the other twenty-three. The flat-rate server bill doesn't change either way.

use-cases / wake-agent-at-3am / mechanism

Two cron entries, one short-lived container

There is no warm pool, no scheduler service, no glue daemon polling for work. A hoody-cron entry POSTs to hoody-agent's spawn URL at 02:59. The agent does its run and exits. A second cron at 04:01 calls DELETE to be sure the container is gone. That is the whole machine.

POST cron.hoody.com/users/root/entries

Wake trigger · 02:59

// Cron entry that fires once a day and POSTs the spawn requestPOST cron.hoody.com/users/root/entries{ schedule: "0 3 * * *", command: "curl -X POST $AGENT_URL -d @prompt.json", comment: "billing-reconcile · 3am wake"}

fires at 02:59 →

POST api.hoody.com/api/v1/projects/$PID/containers

Spawn agent · ai + hoody_kit

// The agent boots, reconciles yesterday's invoices, writes notes, exitsPOST api.hoody.com/api/v1/projects/$PID/containers{ name: "billing-reconcile-$(date +%s)", ai: true, hoody_kit: true, autostart: false}

container exits, second cron fires at 04:01 →

DELETE api.hoody.com/api/v1/containers/$CID

Teardown · 04:01

// Belt-and-braces: a second cron asserts the container is goneDELETE api.hoody.com/api/v1/containers/$CID// Response from hoody-containers200 OK · container deleted

Two cron rows in a database. One agent image. The container only exists for the work, then it stops existing. No warm pool, no scheduled-task primitive, no lifecycle daemon you have to operate yourself.

use-cases / wake-agent-at-3am / night

What the night actually looks like

Five moments. The agent is alive for the middle three. Outside this hour the row in the containers table is gone.

02:59Cron · wake
Cron entry billing-reconcile-wake fires. It POSTs to api.hoody.com with ai: true and hoody_kit: true. A fresh container spins up with a clean filesystem and the agent's prompt loaded.
03:02Agent · read
The agent reads yesterday's billing-exceptions table over Hoody SQLite and asks an LLM to cluster the rows by reason code — either through the Hoody AI Gateway (provider cost + 5%, drawn from your AI Balance) or BYO key direct to Anthropic / OpenAI / your provider. No file-share mounts. Just URLs.
03:31Agent · write
It writes a single triage note per cluster back to the same SQLite URL, then sends one notification with the daily summary. Total wall time so far: about thirty minutes.
03:58Agent · exit
The agent process returns 0 and the container exits on its own. Hoody-containers marks it stopped. From this second forward, nothing about the agent is running, warm, or billed.
04:01Cron · retire
A second cron entry fires DELETE on the container id. If the agent already exited, this is a no-op 200 OK. If it hung, the container is torn down anyway. Idempotent and unsupervised.

Five timestamps, two cron rows, one container that lives for sixty-two minutes. The night runs itself, and you find out it ran by reading the triage note in the morning.

use-cases / wake-agent-at-3am / powers

Why this lifecycle shape works

An always-on worker is the wrong shape for a job that runs once a day. On Hoody the substrate is flat-rate — the win isn't per-second billing, it's no warm pool, no scheduler service, no glue daemon to operate.

Idle costs nothing extra

The container does not exist between runs

There is no warm pool sitting in memory. No 'scheduled task' service holding state. The row in the containers table is gone for twenty-three hours of the day. The flat-rate server you already rent runs the work; idle hours don't generate a separate line item.

No per-run line item

The server bill doesn't change

Hoody bills the box, not the runtime. A 60-minute nightly agent and a 24/7 always-on worker land on the same flat-rate server invoice. The win isn't 'pay only for what you use' — it's not paying twice for warm-pool overhead you don't need.

No lifecycle code

Two cron rows, no glue daemon

You do not write a wake-up Lambda, a 'spin the container' worker, or a watchdog that retires it. Hoody-cron POSTs. Hoody-containers spawns. The agent exits. A second cron POSTs DELETE. That is the entire surface area.

use-cases / wake-agent-at-3am / economics

The cost of an idle agent

Most agent platforms keep the worker warm twenty-four hours a day so it is ready in under a second. For a 3am batch job that is exactly the wrong tradeoff. Cold-spawn in a few seconds is fine when the schedule is yours.

Always-on agent24h × 30 days

720h / mo

An always-on agent container, or a warm-pool seat reserved for an agent that runs once a day, is alive 720 hours a month. 719 of those hours, it is doing nothing.

Idle is the line item on per-second platforms

Wake-and-retire1h × 30 days

30h / mo

A short-lived container spawned by a cron entry exists for one hour a night. Thirty hours a month, total. The agent process returns 0 and the row in the containers table is gone.

MON02:59 → 04:0162m alive
TUE02:59 → 04:0060m alive
WED02:59 → 03:5858m alive
THU02:59 → 04:0061m alive
FRI02:59 → 04:0060m alive
SAT02:59 → 03:5959m alive
SUN02:59 → 04:0060m alive

Server bill unchanged

Hoody bills the server, not the runtime. The 'alive' column shows when the agent existed each night — the same flat-rate server runs whether it's there or not. Pricing starts at $29/month and varies by spec, region, and rental duration.

use-cases / wake-agent-at-3am / punchline

An agent that exists only when there's work for it to do.

Hours alive per day1h02:59 → 04:01, then gone

Server bill change0Flat-rate, alive or idle

Lifecycle code you write0Two cron rows, no daemon

See the spawn API

use-cases / wake-agent-at-3am / replaces

What this replaces

The patterns that pay for an agent to exist around the clock. On Hoody, the agent runs inside the flat-rate server you already rent — no warm pool, no scheduler service, no per-second meter.

Always-on agent containers23 idle hours, billed at the active rate
AWS Lambda warm-poolsPay to keep cold-starts away from cron
Modal Labs scheduled tasksClosed runtime, opaque billing
Custom warm-cold lifecycle codeThree weeks to write, six months to debug
Polling /spawn endpointsA second cron whose only job is launching the first
Hetzner GPU box always running$200/mo for one daily inference

use-cases / wake-agent-at-3am / cta

An agent that exists only when there's work for it to do.

Read the docs

use-cases / wake-agent-at-3am / related

Read the others

Sixty containers on one server

One bare-metal box runs dozens to hundreds of Hoody containers. KSM and BTRFS dedup make the marginal cost near zero.

Containers·Snapshots

Onboard a developer with one link

A new engineer joins on Monday. You send one URL. They open it on whatever laptop they have and they're in a fresh container cloned from your developer-baseline snapshot — code, deps, env, seed data, VSCode-in-browser. Writing code in five minutes, not setting up.

Snapshots·Containers·Terminal·Files

API endpoints that materialize on demand

A wildcard exec script catches the call, asks an LLM to write the handler, runs it in a V8 sandbox, and saves the route. The next call is native.

Exec·Agent·Code·Files

Branch computers like Git

Snapshot a running container — files, processes, memory. Restore in seconds. Fork via /copy. Branching, but for the entire machine.

Snapshots·Containers

Real VS Code on your phone

The Code Orchestrator spawns a VS Code instance on the container and serves the editor over a normal HTTPS URL. Any device with a browser can open it. The work lives in the container, not on the device.

Display·Terminal·Files·Containers+1

AI agents that spawn other AI agents

A research agent posts to /api/v1/projects/$PID/containers to start a child container, then calls the child's agent URL like any other HTTP service. Sub-agents spawn their own sub-agents the same way. No orchestrator framework, just URLs.

Agent·Exec·Containers

One sandbox per customer, automatically

An exec script catches your signup webhook, copies a fresh-customer container, and hands the new tenant their own URL. Isolation is the operating system, not a tenant_id column.

Containers·Snapshots·Exec·Files

Wake up to a finished prototype

Hand the agent a paragraph at midnight. It spawns its own containers, snapshots before risky steps, and posts to your notification webhook at sunrise.

Agent·Snapshots·Containers·Browser+2

Emergency production fix from your phone

PagerDuty wakes you. Open the terminal URL on your phone. PATCH the snapshot from before the bad deploy. Production is back. No bastion, no VPN, no laptop.

Terminal·Snapshots·Network

Tail production logs to a URL anyone can curl

One pipe URL. Up to 256 readers. Three engineers tail the same incident at once with no bastion, no Datadog seat, no log forwarder.

Pipe

Push one build to thirty CI workers at once

The build container streams the tarball to a pipe path with ?n=30. All thirty test workers curl the same URL. Bytes go through once, fanned out.

Pipe

Watch your agent think from the coffee shop

Your agent runs at home. You're at a café. Pipe each event of the loop through Hoody Pipe and curl the same path from your phone — the trace lands character by character. No SSH, no dashboard, no upload.

Pipe·Agent

Move 200GB between clouds with two curls

pg_dump | gzip | curl from Frankfurt. curl | gunzip | psql in Singapore. Bytes flow through the pipe with zero disk in the middle.

Pipe

Send a teammate a database state in one line

pg_dump streams straight into their psql. No file uploaded, no link shared, no download. The pipe routes the bytes through.

Pipe

Stream LLM tokens to anything that reads HTTP

Step 3 streams tokens with curl -T -. Step 4 curls the same path. Tokens move generator to consumer at line speed. No SSE plumbing, no broker.

Pipe·Agent

A progress bar your boss can spectate without joining

Append ?progress to the pipe URL. Anyone who opens it gets a live HTML dashboard — bytes, speed, ETA, state. Up to fifty spectators, none consuming a receiver slot, none touching the stream.

Pipe

The webhook fan-out you didn't have to build

Stripe POSTs to a pipe path with ?n=12. Twelve subscribers curl the receiver URL with ?n=12. The pipe holds the event until everyone is connected.

Pipe·Exec

A CI cache that's just two curl commands

tar | zstd | curl puts node_modules into a pipe. Twenty downstream jobs curl | zstd -d | tar x. No S3 bucket, no cache action, no egress bill.

Pipe·Containers

Drag-drop uploads into your script

hoody-pipe serves a web upload form at every path. Drag a file onto the page, your script reads the bytes from stdin. Zero upload code, no S3 bucket, no presigned URLs.

Pipe·Exec

Broadcast a workshop to 200 viewers from your laptop

ffmpeg streams your screen to a pipe path with ?n=200. Each attendee curls the URL into a browser tab. No platform, no logins, no upload.

Pipe

Inter-container IPC without the message broker

Container A writes to a pipe path. Container B reads from the same path. Backpressure is the connection. No Redis, no queue, no broker.

Pipe·Containers

Tail your agent on the train, get pinged when it lands

The agent streams its trace to a pipe path you can curl from your phone. When it finishes, its last act hits hoody-notifications and your phone buzzes. Two URLs and a buzz — no SDK, no client app, no dashboard.

Pipe·Agent·Notifications

A microphone over HTTP, in two terminals

ffmpeg captures the mic, pipes to a URL. The other end curls and plays the audio. No Zoom, no SDK, no signaling server.

Pipe

Five agents, five pipes, one verdict

A panel of five models reviews the same input. Each runs in its own container and streams its verdict to its own pipe path. A judge process curls all five in parallel and tallies the result.

Pipe·Agent·Containers

Replay this morning's incident to the whole team

Snapshot the incident-time logs in hoody-files. Replay them through a Hoody Pipe URL with ?n=8. Eight engineers curl the same path and watch the cascade fire in lockstep — the post-mortem is a synchronized stream, not a Confluence doc.

Pipe·Files

The fastest 'send me that file' you've ever typed

A teammate pings for a 4 GB dump. Slack rejects it, Drive needs a share request. You type curl -T file …; they type curl … > file. The bytes move directly between disks — no upload bar, no link to share.

Pipe

Run a local LLM, serve it to your whole fleet

One GPU runs llama.cpp. Its tokens stream into a pipe path with ?n=50. Fifty containers curl the same URL and split the stream.

Pipe·Daemon

A live metrics dashboard with no metrics backend

Each container's monitoring loop curls a metric to a pipe URL. The dashboard curls the same URL with ?progress and renders the SSE stream.

Pipe

The cron job that deletes itself when you're done

POST a managed cron entry with expires_at set 48 hours out. The job runs on schedule, then removes itself — no reminder, no cleanup PR, no stale entry.

Cron

Snapshot the container right before the nightly migration

A hoody-cron entry that fires at 02:55 UTC, curls the snapshots URL, and names the artifact pre-migration-2026-05-04. Five minutes later the migration runs. If it succeeds, the snapshot sits idle and costs nothing. If it fails, you restore in 30 seconds with a single PATCH.

Cron·Snapshots

A separate crontab for every customer, automatically

Each tenant gets their own container and their own hoody-cron service. Customer A's 9am digest fires on time even when customer B's job hangs for 40 minutes, because they aren't on the same crontab.

Cron·Containers

Daily rollups without an orchestrator

Raw events pile up in a sqlite URL. Every night a cron entry curls an exec endpoint, the script runs the rollup SQL, writes the daily table back. No DAG, no Airflow Postgres, no scheduler dashboard.

Cron·SQLite·Exec

A crontab per branch, deployed with the code

Your repo checks in `.hoody/crontab`. The deploy script PUTs that file to the new container's Cron API. Each branch gets its container, its filesystem, its schedule.

Cron·Containers

On-call escalation that ages out with the shift

POST a cron entry with expires_at = shift end. When the shift ends, the entry deletes itself. The next on-call posts their own.

Cron·Notifications

Hourly scrape, daily digest, weekly archive — one container

Three lines in one crontab: hourly browser scrape into SQLite, daily exec digest, weekly archive to files. Flat-rate server, three rhythms, no scheduler service.

Cron·Browser·SQLite·Files

Let your customers BYO their own cron schedule

Customers POST their own 5-field expressions; their crontab lives in their container, isolated. You don't validate against a global queue.

Cron·Containers

Schedule the agent, not the script

A 5-field cron entry curls hoody-agent with a prompt instead of running a fixed script. Today is the last day of the month — the agent figures it out. The data shape changed — the agent figures it out.

Cron·Agent

A heartbeat for the silent jobs

Each cron run POSTs a heartbeat to a notifications endpoint. A second cron checks last-heartbeat and pages on silence. Silence is the alert.

Cron·Notifications

Keep the last 24 hours as 24 snapshots

An hourly cron POSTs a snapshot named with the hour. After 24 hours each new snapshot overwrites yesterday's at the same hour. The 24-floor time machine.

Cron·Snapshots

Replay this morning's webhooks at the same time tomorrow

You captured 30 minutes of real Stripe traffic into a hoody-files folder. One cron entry replays it against staging at 9am every weekday — same volume, same payloads, same time-of-day pressure.

Cron·Files·Exec

Edit your crontab from a phone, in the airport

Open the cron URL on your phone in the gate area. Tap a row, change a single field of the cron expression, hit Save. PATCH lands. The job fires tonight on the new schedule. No SSH session, no jump box, no laptop.

Cron·Terminal

A scheduled digest that fans out to 200 inboxes

Cron at 9am POSTs to an exec script that builds the digest and curls a pipe URL with ?n=200. Two hundred recipients hit the same URL once.

Cron·Exec·Pipe

Mute the flaky job without losing it

PATCH /entries/[id] [ enabled: false ]. The job stays in your crontab waiting to be fixed. No deletion, no rewrite, no lost context.

Cron

An agent that grades yesterday's agents

A nightly cron POSTs to the supervisor agent with yesterday's agent traces from SQLite. The supervisor scores each one. Cron is the supervisor.

Cron·Agent·SQLite

Cleanup jobs that schedule their own retirement

The cleanup script checks if there's anything left to clean. When the directory is empty, it DELETEs its own cron entry. Job's done, job's gone.

Cron·Files

Roll your TLS certificates without an SSH session

Cron weekly: POST to an exec script that runs certbot, posts the new cert to the proxy via PATCH. No shell session, no key, no jump host.

Cron·Exec

A weekly canary that tries to break production

Sunday 7am cron wakes a Hoody Agent in a fresh container against a snapshot of prod. It runs the OWASP top twenty, fuzzes the API, and writes a findings report to a URL by 9am. Container retires.

Cron·Agent·Browser·Snapshots

The hobby-project graveyard you can afford to keep alive

Eleven half-finished side projects on Heroku is eleven dynos at $5–7 each. On Hoody it's eleven containers on one $29 bare-metal box. Idle costs zero, the URL wakes the container in milliseconds, and the chess engine nobody uses still runs.

Containers

A preview environment per pull request, all month

Each open PR gets its own clone of a snapshot. The container wakes when reviewers click the link; idle PRs cost nothing.

Containers·Snapshots

Run a 12-product portfolio from one bare-metal box

Twelve isolated containers, each its own SaaS, share one $49 bare-metal server — a step above the $29 entry tier, chosen here for the RAM headroom fifty containers want. Per-product margins go from negative to nice.

Containers

Kill the staging-server tax

Stop paying for a duplicate of production. Snapshot the prod container, branch staging from it on demand, freeze it back to disk when nobody's testing. Three environments, one machine, one bill.

Containers·Snapshots

Forty client sites, one rent, one dashboard

Each client site lives in its own container; you bill them per-site, you pay the host once. The math finally works for agencies.

Containers·Workspaces

Replace the E2B bill with the bare metal you already rent

Your agents stop renting compute by the second from E2B/Modal/Daytona. They use containers on the box you already have.

Containers·Agent·Exec

Idle staging costs nothing, so staging stops getting deleted

Staging used to die because it was expensive to keep around. When idle is free, staging gets to live — even the one a teammate touched 90 days ago.

Containers·Snapshots

Per-customer sandboxes at fleet scale

Eight hundred isolated customers on three bare-metal servers — one flat-rate monthly bill, no per-tenant meter. Each tenant gets a real container with its own kernel namespace, filesystem, and URL. Idle containers cost nothing on top of the server you already pay for.

Containers·Snapshots·Exec

The CI cache that's not an S3 line item

Cache files live in /files on the box you already rent. Workers PUT and GET tarballs over HTTP. No S3 bucket, no egress, no third vendor — the bytes never leave the box.

Files·Containers

Fifty demo environments for fifty sales calls

Each prospect gets a real, isolated copy of your product seeded with their data. Cloned from a snapshot. Theirs to keep for a week.

Containers·Snapshots

Wake an agent at 3am, retire it at 4

Two cron entries, one short-lived container

What the night actually looks like

Why this lifecycle shape works

The container does not exist between runs

The server bill doesn't change

Two cron rows, no glue daemon

The cost of an idle agent

What this replaces

Read the others

Sixty containers on one server

Onboard a developer with one link

API endpoints that materialize on demand

Branch computers like Git

Real VS Code on your phone

AI agents that spawn other AI agents

One sandbox per customer, automatically

Wake up to a finished prototype

Emergency production fix from your phone

Tail production logs to a URL anyone can curl

Push one build to thirty CI workers at once

Watch your agent think from the coffee shop

Share your screen with a URL, not a meeting invite

Move 200GB between clouds with two curls

Send a teammate a database state in one line

Stream LLM tokens to anything that reads HTTP

A progress bar your boss can spectate without joining

The webhook fan-out you didn't have to build

A CI cache that's just two curl commands

Drag-drop uploads into your script

Broadcast a workshop to 200 viewers from your laptop

Inter-container IPC without the message broker

Tail your agent on the train, get pinged when it lands

A microphone over HTTP, in two terminals

Five agents, five pipes, one verdict

Replay this morning's incident to the whole team

The fastest 'send me that file' you've ever typed

Run a local LLM, serve it to your whole fleet

A live metrics dashboard with no metrics backend

The cron job that deletes itself when you're done

Snapshot the container right before the nightly migration

A separate crontab for every customer, automatically

Daily rollups without an orchestrator

A crontab per branch, deployed with the code

On-call escalation that ages out with the shift

Hourly scrape, daily digest, weekly archive — one container

Let your customers BYO their own cron schedule

Schedule the agent, not the script

A heartbeat for the silent jobs

Keep the last 24 hours as 24 snapshots

Replay this morning's webhooks at the same time tomorrow

Edit your crontab from a phone, in the airport

A scheduled digest that fans out to 200 inboxes

Mute the flaky job without losing it

An agent that grades yesterday's agents

Cleanup jobs that schedule their own retirement

Roll your TLS certificates without an SSH session

A weekly canary that tries to break production

The hobby-project graveyard you can afford to keep alive

A preview environment per pull request, all month

Run a 12-product portfolio from one bare-metal box

Kill the staging-server tax

Forty client sites, one rent, one dashboard

Replace the E2B bill with the bare metal you already rent

Idle staging costs nothing, so staging stops getting deleted

Per-customer sandboxes at fleet scale

The CI cache that's not an S3 line item

Fifty demo environments for fifty sales calls