Plain-Markdown agent instructions
Write the agent’s job in Markdown instead of filling out a rigid workflow builder. The product presents this as a way to create specialized agents for sales, support, growth, engineering, and other repeatable work.
Cronloop
Cronloop is a platform for running AI agents on recurring schedules. It lets you define the job in plain Markdown, run agents with Codex or Claude Code, and monitor each run live from the app or via ChatGPT and Claude.
What Cronloop does
Cronloop is a platform for running AI agents on a schedule. Instead of asking an agent to do a one-off task, you describe a recurring job in plain Markdown, choose Codex or Claude Code, and let it keep running in a loop.
The product is built for work that repeats over time: prospect outreach, support triage, content updates, issue handling, and similar operational tasks. Cronloop shows each run live, keeps a memory between runs, and can be used directly in the Cronloop app or through a hosted MCP server connected to ChatGPT or Claude.
Features
Model and provider choice
Choose between Codex and Claude Code for the agent runtime. Cronloop says it works with your existing subscriptions or with provider API keys.
Recurring schedules
Schedule runs from every five minutes to once a week. The site also shows examples such as every 30 minutes, every hour, and every morning.
Durable agent memory
Each agent keeps a memory between runs, and the MCP tools expose read, write, and delete actions for that durable memory.
Live runs and run history
Watch each run live and review the recent history afterward. The dashboard examples show in-progress status, skipped runs, completed work, and timestamps for past runs.
Hosted MCP access and tool integrations
Connect agents to common tools through a broad catalog and through a hosted MCP server. The source lists apps and systems such as Gmail, HubSpot, Notion, GitHub, Zendesk, Google Calendar, and many others.
Use cases
Outbound prospecting
Set an agent to find new prospects on a schedule, enrich them, send outreach, and log results to tools like HubSpot. The home page shows a prospect-outreach agent running every 30 minutes.
Support triage
Use an agent to read new support tickets, reply from help docs, and escalate sensitive cases to a human. The MCP page gives this as a concrete example for Zendesk and similar support workflows.
Content and SEO maintenance
Have an agent review fresh performance data, draft content updates, and publish changes to a CMS on a recurring cadence. The home page frames this as a way to grow organic traffic with scheduled updates.
Engineering task automation
Pick up assigned engineering issues, write fixes and tests, and open pull requests on a schedule. The source positions this as a recurring automation for development work tied to systems like GitHub and issue trackers.
Assistant-driven operations
Ask an assistant connected through MCP to create agents, pause runs, review failures, or update memory without opening the dashboard. This fits teams that already work inside ChatGPT or Claude.
Pros and Cons
Pros
- Supports recurring agents rather than only one-time prompts.
- Lets you describe work in plain Markdown, which is a low-friction way to define a job.
- Includes live run visibility and run history so you can see what happened during execution.
- Agents retain memory between runs, which is useful for ongoing workflows.
- Can be accessed from ChatGPT or Claude through a hosted MCP server with OAuth sign-in.
Cons
- The public pages do not provide a complete pricing or limits breakdown beyond the Free and Pro plan highlights.
- Integration details are broad in the source, but the site does not document every third-party connection or setup requirement in depth.
- The pages emphasize operational workflows, but they do not cover many team, admin, or governance features in detail.
FAQ
What kinds of schedules does Cronloop support?
Cronloop is designed to run recurring AI agents on a schedule. The source shows schedules from every five minutes up to once a week, with individual examples such as every 30 minutes or every morning.
How do you set up an agent?
The product lets you describe the job in plain Markdown, then choose Codex or Claude Code as the agent runtime. Runs execute in a fresh sandbox and can be watched live as they progress.
Can I use Cronloop from ChatGPT or Claude?
Cronloop’s MCP server lets you connect Cronloop to ChatGPT, Claude, or any MCP client that supports remote servers. The connection uses OAuth sign-in, so there is no key to copy into the client.
Does each agent keep state between runs?
Yes. The source says every agent keeps memory between runs, and the MCP tools include reading, writing, and clearing that durable memory.
Is there pricing information available?
The public source does not describe a full pricing page or all plan details. It does show a Free plan and a Pro plan, plus the note that Cronloop works with provider subscriptions or API keys.
Quick Facts
- Category
- AI agent automation
- Primary use
- Scheduled recurring work
- Interfaces
- Cronloop app and hosted MCP server
- Agent runtimes
- Codex and Claude Code
- Source domain
- cronloop.ai
- Pricing signal
- Free and Pro plans are shown on the site
Alternative a Cronloop
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Liam
Liam is an AI copilot for managing inboxes, writing replies, prioritizing email, and scheduling meetings. It is offered free for individuals, with custom pricing for teams and enterprise.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Gemma AI
Gemma AI is a phone call reminder app that calls you with scheduled reminders instead of push notifications. It helps people who want a more direct way to stay on schedule, with Google Calendar sync and conversational call interactions.