OpenClaw is the agent you chat with. Cronable is where the operation runs.
OpenClaw is an open-source personal agent that lives in your chat apps and has a scheduler of its own. Cronable is built for the other half of the job: the dozens of automations that have to fire on time, wait for each other, and leave a record you can check without asking.
The short answer
OpenClaw is a remarkable assistant: one gateway on your own machine, reachable from WhatsApp, Telegram, Slack and dozens of other chat apps, able to run commands, browse the web and remember what you told it. Its automations run agent turns or plain commands on a schedule, back off after errors and alert you when a job keeps failing.
Where they differ is the workflow itself. OpenClaw’s automations each run on their own trigger; multi-step pipelines need its optional Lobster plugin, and stored credentials sit in plaintext config files unless you move them to SecretRefs. Cronable makes the workflow the thing you look at: a live canvas of every job, coloured by state, where a step runs only after its parent succeeded, its output flows into the next one, and a failure goes to a handler instead of down the line.
And you do not have to choose. A terminal step can run openclaw agent like any other command, so an OpenClaw agent becomes one step in a Cronable workflow — on a schedule, with a timeout, retries and a record of every run.
Cronable vs OpenClaw
Where Cronable and OpenClaw actually differ, capability by capability.
| Capability | Cronable | OpenClaw |
|---|---|---|
| What it is | A workflow orchestrator for your own machine | A personal AI agent you talk to through chat apps |
| Runs on your own machine | Yes — a Mac or Windows app, or a server | Yes — self-hosted on your machine or a server |
| Schedules | Hourly, daily, weekly and monthly points, with a timezone | One-shot, interval, cron, on-exit, stream and condition-watch automations |
| Run a step only if the previous one succeeded | Yes — chain on parent success and pass its output in | Multi-step pipelines need the optional Lobster plugin; automations themselves don’t chain on another job’s success |
| Where you see your automations | A live, draggable canvas of every job, coloured by state | Chat, the CLI, and an automations page in its Control UI |
| Steps that need no model | Shell, SSH, HTTP, SQL, email and 123 integrations run as plain steps | Agent turns, or plain shell-command and script jobs with no model call |
| Run history | Every run, with status, timing, output and live, secret-masked logs | Run records with status, kept for 7 days, up to 2,000 per job |
| Retries and failure alerts | Retry with backoff, a timeout per job, de-duplicated alert emails and a handler job | Backoff after errors; failure alerts after 2 consecutive failures by default |
| Stored credentials | AES-256-GCM encrypted in a local database, masked from logs and output | Plaintext in its config files unless you move them to opt-in SecretRefs |
| What can start a run | Schedules, parent success, SaaS webhooks, new files, new mail, sheet rows and more | Schedules, condition watchers, inbound webhooks, Gmail and IMAP mail, MCP events and chat messages |
| Chat apps | Posts to Slack, Teams, Telegram, Discord, SMS and email; a Telegram message can start a job | 30+ chat channels, from WhatsApp and iMessage to Signal and Matrix |
| Team controls | Business adds SSO, role-based access, an audit trail and four-eyes change approval | Roles, sign-in through Cloudflare Access with your identity provider, and an audit ledger; one gateway is one trust boundary |
| Licence | Commercial, on-premises | MIT, free and open source |
What it is
Cronable
A workflow orchestrator for your own machineOpenClaw
A personal AI agent you talk to through chat appsRuns on your own machine
Cronable
Yes — a Mac or Windows app, or a serverOpenClaw
Yes — self-hosted on your machine or a serverSchedules
Cronable
Hourly, daily, weekly and monthly points, with a timezoneOpenClaw
One-shot, interval, cron, on-exit, stream and condition-watch automationsRun a step only if the previous one succeeded
Cronable
Yes — chain on parent success and pass its output inOpenClaw
Multi-step pipelines need the optional Lobster plugin; automations themselves don’t chain on another job’s successWhere you see your automations
Cronable
A live, draggable canvas of every job, coloured by stateOpenClaw
Chat, the CLI, and an automations page in its Control UISteps that need no model
Cronable
Shell, SSH, HTTP, SQL, email and 123 integrations run as plain stepsOpenClaw
Agent turns, or plain shell-command and script jobs with no model callRun history
Cronable
Every run, with status, timing, output and live, secret-masked logsOpenClaw
Run records with status, kept for 7 days, up to 2,000 per jobRetries and failure alerts
Cronable
Retry with backoff, a timeout per job, de-duplicated alert emails and a handler jobOpenClaw
Backoff after errors; failure alerts after 2 consecutive failures by defaultStored credentials
Cronable
AES-256-GCM encrypted in a local database, masked from logs and outputOpenClaw
Plaintext in its config files unless you move them to opt-in SecretRefsWhat can start a run
Cronable
Schedules, parent success, SaaS webhooks, new files, new mail, sheet rows and moreOpenClaw
Schedules, condition watchers, inbound webhooks, Gmail and IMAP mail, MCP events and chat messagesChat apps
Cronable
Posts to Slack, Teams, Telegram, Discord, SMS and email; a Telegram message can start a jobOpenClaw
30+ chat channels, from WhatsApp and iMessage to Signal and MatrixTeam controls
Cronable
Business adds SSO, role-based access, an audit trail and four-eyes change approvalOpenClaw
Roles, sign-in through Cloudflare Access with your identity provider, and an audit ledger; one gateway is one trust boundaryLicence
Cronable
Commercial, on-premisesOpenClaw
MIT, free and open sourceWhat you get by running it on your own machine
Chains that wait for success
A step fires only when its parent succeeded, receives the parent’s output, and a failure branches to a handler job instead of running the rest on broken state. Agent steps sit next to shell, HTTP, database and integration steps in one workflow, on one canvas.
Every run recorded, with live logs
Each run keeps its status, timing, output and secret-masked logs, streamed live while it happens. Chain a job to fire only when its parent succeeded, retry with backoff, and route a failure to a handler job instead of down the pipe.
Secrets encrypted on your own disk
Credentials are AES-256-GCM encrypted in a local database, referenced from jobs only as {{ $secrets.NAME }}, and masked out of logs, output and the live stream. No third party holds the key.
Your AI agents, on a schedule
Run Claude Code, Codex or Gemini CLI headlessly in a folder on your machine, under the AI account you already use, with a timeout that stops the agent and everything it started. Its final answer becomes the run’s output and flows into the next step.
Governance built in, not bolted on
On Business, Cronable adds role-based access, an audit trail of who changed what, OIDC single sign-on with your own identity provider, and four-eyes approval, so, once you turn it on, a job change needs a second pair of eyes before it can run. On every plan, each job stays a YAML file you can diff and roll back.
Say what you want; it builds the pipeline
Type “every morning, check yesterday’s Stripe refunds and post the total to Slack” and the built-in assistant builds the whole job — the steps, the schedule, the credentials it needs and what happens when one fails — wired and ready to run. You review it on the canvas and change anything. On every plan, including Free.
Cronable and OpenClaw
Does Cronable work with OpenClaw?
Yes. A terminal step can run openclaw agent with a message, and the agent’s reply becomes the run’s output — so the next step can act on it, and a failure can retry or go to a handler. On Business you can also turn on Cronable’s MCP server, so an agent that speaks MCP can create and manage jobs from its own chat, under your roles and audit log.
OpenClaw already has cron. What does Cronable add?
Structure around the runs. A Cronable step can wait for the one before it to succeed and take its output, with no plugin to install; a failure branches to a handler job; credentials are encrypted on disk and masked out of every log; and every workflow sits on one live canvas, so last night’s failure is visible before you think to ask. Add 123 built-in integrations and, on Business, single sign-on, role-based access, an audit trail and four-eyes change approval.
Is Cronable an open-source OpenClaw alternative?
No. Cronable is a commercial product that you run entirely on your own infrastructure; its source is not published. OpenClaw is MIT-licensed. Cronable has a Free plan with 6 jobs, all built-in job types, git sync and encrypted secrets.
How does Cronable handle security?
The engine listens only on your machine’s own loopback address, every request needs a login, it refuses to run as root, and secrets are AES-256-GCM encrypted and masked from logs, output and the live stream. Jobs still run as your user with your access — that is the point — so treat it like a shell on the box and give each job only what it needs.
Can I still run things from chat?
Yes, in a few ways. A Telegram bot message can trigger a job, the built-in assistant builds jobs from a plain-English description, and from Basic up remote control lets you drive your install from a browser anywhere, without opening a port.
Which AI models can a Cronable step use?
Claude Code, Codex and Gemini CLI run headlessly as jobs, and model steps can call Claude, OpenAI, Gemini, Ollama or any OpenAI-compatible endpoint — all on your own accounts, chosen per step.
Automate your operations.
Cronable is launching soon. Join the waitlist and we’ll email you the moment self-serve accounts — and the apps for Mac, Windows and Linux — go live.